**STAT 206: Statistics for Elementary Education**

## STAT206

### Instructor

Rebecca Durfee

### Required Text

Stat 206: Statistics for Elementary Education, by Rebecca Durfee

### Grading Policy

**Quizzes: 20%**Quizzes will be assigned throughout the semester. Each quiz will be due one week after the material is presented. Students may use notes to complete the quizzes, and students may work cooperatively. Quizzes are found in a packet distributed the first day of class. The lowest quiz grade will be dropped.**Homework: 20%**Homework assignments will be assigned throughout the semester. The same rules apply for homework assignments and quizzes. The lowest homework assignment will be dropped.**Exams: 60%**Three unit exams will be given, each counting 15%. The final exam is not cumulative, but is an in-class project worth 15% of the final grade.

### Schedule

- Exam 1: 9/26
- Exam 2: 10/24
- Exam 3: 11/30
- Final: 12/5 and 12/7

### Course Objectives

#### Unit 1

- If given a scenario with multiple outcomes, students will determine the probabilities of simple events using tree diagrams and sample spaces.
- Students will determine the appropriate graphing technique(s) to represent given data and use Excel to create those graphs.
- Students will determine which measures of central tendency are appropriate for a given data set and calculate those values.
- Given normal data, students will calculate what proportion of the data falls within certain ranges using the empirical rule.
- Students will recognize and employ different sample collection techniques and determine which methods are useful and which should be avoided.
- Students will calculate and interpret correlation coefficients and predict average response variables using linear regression.

#### Unit 2

- Given normal data, students will determine at which percentile a given value falls.
- Given normal data, students will determine which value corresponds to a given percentile.

#### Unit 3

- Students will determine and utilize the correct procedure for determining confidence intervals for means and proportions.
- Students will determine and utilize the appropriate method for one-sample and two-sample hypothesis testing with means and proportions.

*Last updated: Fall 2017*

**STAT 208: Statistical Thinking**

## STAT208

### Instructor

Rebecca Durfee

### Prerequisite(s)

Completion of a 100-level math course or placement on the placement test.

### Required Text

STAT 208 Statistical Thinking: A book for STAT 208 at Virginia Commonwealth University by Dr. W. Scott Street IV, Dr. James Mays and Becky Durfee

### Calculator

Students will need a graphing calculator and a cell phone or other device compatible with Top Hat.

### Grading Policy

- Top Hat questions, in class: 10%
- Checks for understanding in blackboard: 25%
- Exam 1: 15%
- Exam 2: 15%
- Exam 3: 15%
- Final exam: 20%

### Course Objective

Students will discern between credible and false/misleading information in the age of the Internet. Students will recognize the components of a good study and appropriately analyze data using graphing calculators. Students will effectively interpret and communicate their findings.

### Attendance Policy

I will not take attendance in class. However, every day, two Top Hat questions will be asked, and those responses count as part of your final grade.

*Last updated: Fall 2017*

**STAT 210: Basic Practice of Statistics**

## STAT210

### Instructor

D'Arcy Mays, Ph.D.

### Prerequisite(s)

Satisfactory score on the Mathematics Placement Test, completion of MATH 131 or higher level MATH course, or transfer credit of a college algebra or higher level course.

### Required Text

*Supplement to Basic Practice of Statistics*, *Revised Eleventh Edition* or *Eleventh Edition Update* by D’Arcy P. Mays. You are required to purchase a copy of this supplement and should bring it to lecture regularly. ISBN 9780078044878 or ISBN 9781259425523. There are significant differences between the Eleventh Edition and older editions that will make the older editions difficult to use.

### Calculator

You should have a calculator that you know how to use and should bring this to class regularly. Instructions for using TI-83, TI-83 Plus, TI-84 and TI-84 Plus calculators are given in the supplement, but other calculators are acceptable as well. You will not be allowed to use cell phones on any graded assignment (tests or final exam). Sharing of calculators will not be allowed on any graded assignment and will be considered an Honors violation if observed. The department has a limited number of calculators that can be rented for the semester for $10.00. Go to Harris Hall room 4144 if you are interested.

### Equipment

Top Hat classroom response system. Top Hat will require a paid subscription, and a full breakdown of all subscription options available can be found on their website. Special pricing is available for students enrolled in STAT 210 at the following rates:

- 4 months: $20
- 1 year: $30
- Lifetime: $60

### Grading Policy

Your final average grade will be determined as follows. There will be seven tests, and on non-test days you will answer questions in class using Top Hat. Each of these eight grades will count 12.5% of your final grade (each counts 1/8th of your grade).

There will be an optional final exam. If you choose to take the final exam, it will be graded and the final exam grade will replace any test grade or Top Hat grade that is lower (this could possibly include all eight grades).

Your course letter grade will be based on the ten point scale:

- 90 or above: A
- 80 – 89.99: B
- 70 – 79.99: C
- 60 – 69.99: D
- Below 60: F

### Attendance Policy

You are expected to attend all classes, however attendance is not taken. Missing class on a test day will mean the test grade will be determined from your final exam grade, and missing class on a non-test test will affect your Top Hat grade.

*Last updated: Fall 2017*

**STAT 212: Concepts of Statistics**

## STAT212

### Instructor

Mita Basu

### Prerequisite(s)

Math Placement Test, MATH 151, MATH 200 or MATH 201

### Required Text

Concepts Of Statisticsby Rebecca J. Durfee and Mita Basu

### Calculator

You should have a calculator that you know how to use and should bring this to class regularly. Instructions for using TI-83, TI-83 Plus, TI-84 and TI-84 Plus calculators are posted on Blackboard, but other calculators are acceptable as well. You will not be allowed to use cell phones on any graded assignment (tests or final exam). Sharing of calculators will not be allowed on any graded assignment and will be considered an Honors violation if observed. The department has a limited number of calculators that can be rented for the semester for $10.00. See Samantha Powell in Harris 4144 if you are interested or you can fill out the calculator loan contract form posted on Blackboard and get it to me.

### Grading Policy

There are two tests and each of these two test grades will count 50% of your final grade (each counts 1/2 of your grade). The Final Exam is OPTIONAL and CUMULATIVE. There will be an optional final exam. If you choose to take the final exam, it will be graded and the final exam grade will replace any test grade that is lower (this could possibly include both the test grades). Your course letter grade will be based on the ten point scale:

- 90 or above: A
- 80 – 89.99: B
- 70 – 79.99: C
- 60 – 69.99: D
- Below 60: F

### Course Description

Statistical methods employed in the analysis of business and economic data with applications in decision making. Statistical studies, understanding variation, data collection, descriptive measures, probability, and statistical inference including estimation, testing hypothesis and interval estimation with application to classical models.

### Course Objectives

To gain an understanding and working knowledge of the fundamental concepts of statistical methods, including the summary and description of data, analysis of data, and the use of statistical information as an aid in decision making. To recognize appropriate applications of these statistical methods, to perform the analysis, to explain the results, and to evaluate the findings prepared by others.

*Last updated: Fall 2019*

**STAT 305: Intermediate Statistics**

## STAT305

### Instructor

Amy Kimbrough

### Calculator

A calculator that you know how to use is required for this class. Sharing of calculators will not be permitted on exams.

### Software

Most homework assignments and the group project will incorporate SPSS software; this software isavailable at VCU for FREE for Windows, Mac, etc.

### Grading Policy

Category | Points |
---|---|

Homework | 125 |

Group project | 100 |

Midterm exam | 125 |

Final exam | 150 |

Total | 500 |

A (450 – 500 pts.)

B (400 – 450 pts.)

C (350 – 400 pts.)

D (300 – 350 pts.)

F (0 – 300 pts)

There will be no extra credit assignments.

### Topics/Schedule

Lecture | Date | Topic |
---|---|---|

1 | August 28 | Syllabus, Course Policies, Introduction |

2 | August 30 | Confidence Intervals for a Proportion |

-- | September 4 | No class: Labor Day |

3 | September 6 | Confidence Intervals for a Mean |

4 | September 11 | Errors in Hypothesis Testing |

5 | September 13 | Hypothesis Tests for a Single Parameter |

6 | September 18 | Hypothesis Tests for Two Proportions |

7 | September 20 | Hypothesis Tests for Two Independent Means |

8 | September 25 | Paired T-Tests and Hypothesis Tests for Population Variances |

9 | September 27 | Chi-Square Tests |

10 | October 2 | Chi-Square Tests |

11 | October 4 | One-Way ANOVA |

12 | October 9 | Multiple Comparisons |

13 | October 11 | Randomized Block Design ANOVA |

14 | October 16 | Randomized Block Design ANOVA and Two-Way ANOVA |

15 | October 18 | Two-Way ANOVA |

16 | October 23 | Review |

17 | October 25 | Midterm Exam |

18 | October 30 | Review of Regression |

19 | November 1 | Simple Linear Regression |

-- | November 3 | Last Day to Withdraw |

20 | November 6 | Simple Linear Regression |

21 | November 8 | Multiple Linear Regression |

22 | November 13 | Multiple Linear Regression |

23 | November 15 | Analysis of Covariance |

24 | November 20 | Logistic Regression |

-- | November 22 | No class: Thanksgiving Break |

25 | November 27 | Non-Parametric Analysis |

26 | November 29 | Non-Parametric Analysis |

27 | December 4 | Review and Project Work |

28 | December 6 | Project Presentations |

The final exam is Wednesday, December 13, 1:00 p.m. - 3:50 p.m.

### Attendance Policy

You are expected to attend class regularly and to arrive on time. If you must miss a class for some reason, it is YOUR RESPONSIBILITY to contact a fellow student for the lecture notes; furthermore, if you must miss a class in which an assignment is due or an exam is to be given, it is in your best interest to notify me ahead of time (even if you must call or email right before class begins)! Remember...do not expect me to accept late assignments or to give make-up tests.

*Last updated: Fall 2017*

**STAT 309: Introduction to Probability Theory**

## STAT309

### Instructor

Jenise Swall

### Prerequisite(s)

The prerequisites for the course are MATH 307 (multivariate calculus) and either MATH 211 or MATH 300

### Required Text

The course textbook is Mathematical Statistics with Applications (7th ed.) by Wackerly, Mendenhall, and Scheaffer; the ISBN-13 is 978-0-495-11081-1. If you cannot find a reasonably priced copy of the 7th edition, you can use the 6th edition (ISBN 0-534-37741-6). I advise against using the international 7th edition, as the problems and page numbers may not be the same.

### Calculator

Hand-held scientific calculator: Your calculator does not have to be programmable, nor does it need to be capable of displaying graphics.

### Grading Policy

- Quizzes: 30% (two lowest quiz grades dropped)
- Midterm 1: 20%
- Midterm 2: 20%
- Comprehensive final exam: 30%

### Topics/Schedule

Week of | Topics | Relevant Text |
---|---|---|

18Aug | Intro., events and sets | 1.1-1.6, 2.1-2.5 |

25Aug | Counting rules, conditional prob. | 2.5-2.7 |

01Sep | Independence, Bayes’ rule | 2.7-2.10 |

08Sep | Discrete RVs, expectation, binom. dist. | 2.11-2.13, 3.1-3.4 |

15Sep | Geom. & neg. binomial dists., review | 3.5-3.6 |

22Sep | MIDTERM (24Sep), hyper. & Poisson dists. | 3.7-3.8 |

29Sep | Poisson dist., moment-generating funcs. | 3.8-3.9 |

06Oct | Mgfs & Tchebysheff’s, cont. RVs | 3.9, 3.11-3.12, 4.1 |

13Oct | Cont. RVs, unif. & normal dists. | 4.1-4.5 |

20Oct | Gamma & beta dists. | 4.6-4.8 |

27Oct | Review, MIDTERM (31Oct) | |

03Nov | Moments & Tchebysheff’s revisited | 4.9-4.10, 4.12 |

10Nov | Bivariate & multivariate dists | 5.1-5.3 |

17Nov | Marginal & cond. dists., indep. | 5.3-5.4 |

24Nov | THANKSGIVING BREAK | |

01Dec | Linear functions, covariance, review | 5.5-5.7 |

08Dec | FINAL EXAM (10Dec) |

### Attendance Policy

Attendance and class participation are crucial. I encourage you to not only attend class, but to ask questions, solve example problems with me and your classmates in class, and participate in class discussions. While attendance is not part of your grade, please note that you are responsible for everything discussed in class.

### Homework and Homework Quizzes

There will usually be a (bi-)weekly homework assignment. You should complete the selected problems, and any other problems as necessary to reinforce your understanding of the concepts. Following most assignments, there will be a brief quiz in class. The problem(s) will be taken from the homework, though I may sometimes change minor details. **No make-up quizzes will be given**, but your two lowest homework quiz grades will be dropped. If you are concerned that you may miss multiple homework quizzes due to unavoidable circumstances (e.g., treatment of a medical issue requiring multiple appointments), please contact me as soon as the situation develops so that we can discuss alternatives.

*Last Updated: Fall 2019*

**STAT 310: Intro to Statistical Inference**

## STAT310

### Instructor

Cheng Ly

### Required Text

Mathematical Statistics by Wackerly, Mendenhall, Scheaffer. 7th edition. ISBN-10: 0495-11081-7, ISBN-13: 978-0-495-11081-1. Cengage Learning

### Calculator

Calculators are allowed on homework and exams (TI-86 or below), however, you must show all of your work to receive credit.

### Grading Policy

- Homework/Quizzes: 30%
- 2 Midterm exams: 40%
- Final exam: 30%

Letter grade assignments will be no harsher than the 10% scale (i.e., >90% is a guaranteed A).

### Topics/Schedule

- Chapter 7: Sampling Distributions & the CLT [2.5 weeks]
- Chapter 8: Point Estimators, 8.1-8.4 [1 week]
- Chapter 6: Functions of Random Variables, 6.1-6.4 [1 week]
- Chapter 8: Confidence intervals, sample size, 8.5-8.7 [1 week]
- Chapter 9: Properties of Point Estimators and Methods of Estimation [3 weeks]
- Chapter 10: Hypothesis Testing [2 weeks]

### ExamPolicy

NO MAKE-UP exams unless you have an emergency or legitimate excuse. In the event of an emergency, you must notify me before the exam and provide evidence. **You must have a legitimate excuse otherwise you will receive a 0 on the exam.**

*Last Updated: Spring 2019*

**STAT 314: Applications of Statistics**

## STAT314

### Instructor

Scott Street

### Prerequisite(s)

STAT 210 or STAT 212

### Required Text

*Statistics: The Exploration and Analysis of Data*, Seventh Edition (ISBN 978-0-8400-5801-0) by Peck & Devore, Thompson Brooks-Cole Publishers, 2012 [or use *2016 Custom Edition*: ISBN 978-1-337-03858-4] *Student Solutions Manual* (ISBN 978-1-1115-7977-7), by Peck, Thompson Brooks-Cole Publishers, 2012

### Calculator

A calculator that you know how to use is required for this class. I recommend the TI-83 series, TI-84 series, or TI-Nspire series graphing calculators because they have built-in statistical capabilities. Sharing of calculators will not be permitted.

### Software

Most assignments will incorporate SPSS software; this software isavailable at VCU for FREE for Windows, Mac, etc.

### Grading Policy

Category | Points |
---|---|

Classwork (total combined score) | 100 points |

Projects (total combined score) | 100 points |

TopHat (total combined score) | 100 points |

Test #1 | 100 points |

Test #2 | 100 points |

Test #3 | 100 points |

Total | 600 points |

- A (540 – 600 pts.)
- B (480 – 539 pts.)
- C (420 – 479 pts.)
- D (360 – 419pts.)
- F (0 – 359 pts.)

THERE WILL BE NO EXTRA CREDIT ASSIGNMENTS

### Topics

- Confidence Intervals and Hypothesis Testing using a single sample and for comparing two populations
- Categorical Data Analysis, One-Way Analysis of Variance, Two-Way Analysis of Variance, Multiple Comparisons, Randomized Block Designs
- Simple Linear Regression, Multiple Linear Regression, Variable Selection, Regression Inferences

### Class Structure

This will be a** “flipped” class**. In a traditional class structure, students attend class to listen to the instructor deliver a lecture. They take notes in class, and then they are given classwork to do on their own to reinforce the material covered in the lecture. In a “flipped” class, students listen to the lecture material on their own, and then class time is spent working with the instructor and fellow students on problems.

In this course, to prepare for class you will be expected to watch video recordings of the lectures, which are posted on Blackboard. You should expect to spend approximately 2 hours before each class watching the lecture and example videos, and you should take notes, just as you would during a traditional lecture. In class, we will answer questions based on the concepts introduced in the lectures, and then work together to complete the “classwork” problems. Any problems that you do not finish in class will need to be finished on your own before the assignment’s due date.

**This “flipped” class structure will require you to actively take responsibility for your part of the learning process**. It will be up to you to make sure that you watch the lecture material in advance and not just show up for class and try to “wing” it. The benefit of this class style will be that, instead of showing up for class and passively listening and then trying to solve problems at home on your own with no help, you will be able to do the listening at home and then have the chance to receive help from both your classmates and the instructors as you work through the problems.

To help you assess your understanding of the video lectures and examples, we will have clicker quizzes at the beginning of most classes, so you will want to be sure that you have kept up with the required reading and video watching. At the end of most classes, we will have another clicker quiz to help you assess your understanding of the topics and techniques after our class discussions and problem solving.

### Credit Hour

A credit hour is defined as a reasonable approximation of one hour of classroom or direct faculty instruction and a minimum of two hours out-of-class student work each week for approximately 15 weeks, or the equivalent amount of work over a different amount of time. Credit is based on at least an equivalent amount of work for other academic activities including laboratory work, internships, practica, studio work and other academic work leading to the award of credit hours and is established by individual programs. This definition represents the *minimum* standard. Student time commitment per credit hour may be higher in individual programs. (More information)

### Workload Expectations

This is a four-credit course. Therefore, you are expected to spend at least eight hours each week outside of class in addition to the approximately four hours that you will spend each week in class. While some weeks will not require the full 12 hours of effort, others might require more; however, it is our expectation that the * average* time spent on this course will be approximately 12 hours per week. Be sure that you budget your time (and schedule your work/job hours appropriately) to allow for this workload each week.

### Attendance

You are expected to attend class regularly and to arrive on time. The last day of this class is Monday, December 9; however, we will meet during our assigned final exam time (see course schedule). Important: If you must miss a class for some reason, be sure to contact a fellow student to find out what was discussed in class; furthermore, if you must miss a class in which an assignment is due or a test is to be given, it is in your best interests to notify me ahead of time (even if you must call/email just before class begins)! Remember...do not expect me to accept late assignments or to give make-up tests.

*Last updated: Fall 2019*

**STAT 321: Introduction to Statistical Computing**

## STAT321

### Instructor

Qiong Zhang

### Prerequisite(s)

Statistical concepts from previous coursework in statistics are presumed to be known; there is not time in the course for a theory review.

### Required Text

Introductory Statistics with R (2nd), by Peter Dalgaarde (2008).

### Topics

Topics include data storage and retrieval; data modication and file handling; standard statistical analyses; graphical representation; practical presentation of results; and simulation exercises should time allow.

### Homework

- There will be approximately eight homework assignments.
- Assignments will be uploaded via Blackboard.
- Unless otherwise stated, homework must be uploaded to Blackboard only (no email) by the beginning of class on the due date. Occasionally, the assignment may only require a hardcopy; in these cases I will provide the details for submission. Late homework will not be accepted.

### Take-Home Exams

There will be two take-home exams during the semester intended to test the course material learned up to that point. The second exam will not explicitly test material from that of the first exam; but implicitly you will most likely require those concepts to complete the second exam.

### In-Class Group Contest

There will be one in-class group contest during the semester. Students will be split into five groups (randomly). The members in the winner group will have one extra point added in their final score.

### Bonus Assignments

There will be a few bonus assignments announced during the semester. The assignments are supposed to be more challenging, but much shorter than the homework assignments. The bonus assignments are not required. The first student who sends me the correct answer of the bonus assignments will be able to waive one of the homework assignments.

### Final Exam

There will be an in-class cumulative final exam.

### Grading Policy

Each homework assignment carries equal weight. Missed assignments will receive a grade of zero. The final grade for the course will be determined via a weighting of the scores received on homework and exams in the following manner:

- Homework average: 20%
- Take-home exams: 25% for each
- Final exam: 30%

Tentative grading scale:

- A: 90-100
- B: 80-89
- C: 70-79
- D: 60-69
- F: 0-59

*Last updated: Spring 2015*

**STAT 403: Introduction to Stochastic Processes**

## STAT403

### Instructor

Cheng Ly

### Required Text

*Introduction to Probability Models*, by Ross. 10th edition. ISBN-10: 0123756863, ISBN-13: 978-0123756862. Publisher: Academic Press (Elsevier).

### Calculator

TI-89 or below

### Software

Matlab

### Grading Policy

- Homework: 35%
- In-class exams: 35%
- Final exam: 30%

Letter grade assignments will be no harsher than the 10% scale (i.e., >90% is a guaranteed A). Homework will be assigned and graded about every week or two.

### Topics/Schedule

- Chapter 1: Introduction to probability theory [1 week]
- Chapter 2: Random Variables [2.5 weeks]
- Chapter 3: Conditional Probability and Conditional Expectation [2.5 weeks]
- Chapter 4: Markov Chains [3.5 weeks]
- Chapter 5: The Exponential Distribution and Poisson Processes [3.5 weeks]

*Last updated: Spring 2015*

**STAT 422: Structured Problem Solving Using Statistics**

## STAT422

### Instructor

Mita Basu

### Required Text

Required (any one of the following listed below should be fine) introductory level statistics book such as:

*Statistics: The Exploration and Analysis of Data*, 6th or 7th Edition, Duxbury Press by Devore, Jay and Peck, Roxy*An Introduction to Modern Business Statistics*, Duxbury Press 1999 by Canavos, George C. and Miller, Don M.*Statistics for the Behavioral Sciences*, 4th or 5th edition by Jaccard and Becker

Please note: If you have any one of the above books which are an older or newer edition than what is mentioned above, that should be fine as well.

### Optional References

*The Thinker’s Toolkit*, by Morgan D. Jones*Statistics: A guide to the unknown*(4th edition). Roxy Peck, George Casella, George Cobb, Roger Hoerl, Deborah Nolan, Robert Starbuck, Hal Stern*Saying it with charts*. Gene Zelazny*The Mckinsey Way*. Ethan M. Rasiel

### Course Overview

- Understand, develop and apply analytical frameworks that enable one to structurally think through complex real world problems
- Review basic concepts of statistics (sampling techniques, confidence intervals, significance tests etc.)
- Introduce /review new concepts like regression analysis, DOE, reading ANOVA tables in more details.
- Work through a case from start to end applying analytical and statistical techniques mentioned above
- Group projects involving practical cases where students get to solve a case from scratch using proper analytical and statistical frameworks to come up with recommendations that are effective and can be easily communicated.
- Role playing exercise in class where each group becomes the “client” and the “consultant”. Performance will be evaluated on the strength of the final recommendation and the constructive feedback provided to the other team to make the recommendation even more powerful. No points for nit picking. The whole idea is to keep a positive attitude and add value to the final answer.

### Course Objectives

- Using analytical frameworks to structure and solve complex real world problems
- Using statistics as a tool for quantitative data analysis
- Effective communication through presentation and role playing in class

### Requirements:

Attendance, daily reading and homework, and active participation in class are required to master the material. Reading will be assigned for each class meeting. For each class meeting, you should have read the material, and be prepared to participate in the class discussion. There will be in class pop quizzes and they will be due at the end of class the day they are assigned (more details will be given on the first day of class)

### Attendance Policy

Attendance will be checked at the beginning of each class. You should be seated and ready to begin class at the scheduled starting time. Late arrival should be avoided, but if it occurs, please be respectful of others and be seated quickly to minimize interruptions. See the instructor after class to confirm your attendance. While you are encouraged to ask questions during class, you should not hold any other conversations in class. Doing so is a disruption to other students and will be handled according to the VCU policy for Student Conduct in the Classroom. Other disruptions that should be avoided include getting up and leaving the room during class, etc. Please turn off cell phones or keep them in vibrate mode during lectures.

### Grading

- Pop quizzes: 40%
- Project: 30%
- Presentation: 20%
- Class participation: 10%

- A: 90 or above
- B: 80 – 89.99
- C: 70 – 79.99
- D: 60 – 69.99
- F: below 60

### Tentative Schedule

Week | Topic |
---|---|

1 | Introduction, Syllabus |

2 | Pitfalls of Thinking - Common flaws in day to day thinking |

3 | No class |

4 | Introduction to Hypothesis Driven Thinking/Discuss a case to illustrate use and application of hypothesis based approach |

5 | Problem Restatement - Redefining the problem in a clear and concise manner that should facilitate the problem solving process |

6 | Pros-Cons-Fixes framework |

7 | Divergent/Convergent Thinking Approach |

8 | The Matrix Problem Solving Approach; The Decision/ Event Tree |

9 | Review of Basic Stats concepts-Sampling/ DOE basics |

10 | Review of Confidence Intervals |

11 | Review of Confidence Intervals |

12 | Review of Hypothesis Testing |

13 | Review of Hypothesis Testing |

14 | Review of Chi squared tests |

15 | Review of Chi squared tests |

16 | Review of ANOVA |

17 | No class |

18 | No class |

19 | Review of ANOVA |

20 | Review of Multiple Comparisons |

21 | Review of Regression |

22 | Sample case 1 |

23 | Case 1 continued |

24 | Sample case 2 |

25 | Group project |

26 | Group project |

27 | Group project |

28 | Group project |

29 | Group project |

30 | Group project |

31 | Group project/guest speakers if available |

32 | Project presentations |

*Last updated: Spring 2015*

**STAT 423: Nonparametric Statistics**

## STAT423

### Instructor

Anh T. Bui

### Prerequisite(s)

Basic probability and statistical inference, e.g., STAT 305 or with my permission

### Optional Text

*Applied Nonparametric Statistical Methods*, 4th Edition, Peter Sprent and Nigel C. Smeeton, Chapman & Hall/CRC

### Course Description

The course provides an introduction to statistical inference methods that require relatively mild assumptions about the population distribution. Classical nonparametric hypothesis testing methods (e.g., one-, two-, and multiple-sample methods), association, and extra topics (such as bootstrap, density estimation, and nonparametric regression) will be covered. This course is mainly application-driven. Students are required to use statistical software R for in-class practice and assignments, but no prior knowledge of R is required.

### Homework Assignments

This course has five homework assignments in total. Many homework problems require R for statistical computing. Some problems require descriptions and comments on some results. Homework assignments are due at the beginning of the classes on the due dates. Late submission will not be accepted. You are encouraged to discuss on homework assignments, but you must write your own solutions.

### Grading Policy

Homework (25%), Take-home exam (25%), Midterm in-class exam (25%), Final project (25%), and Class participation.

### Tentative Grading Scale

- A: 90-100
- B: 80-89
- C: 70-79
- C: 70-79
- D: 60-69
- F: 0-59

### Take-Home Exam

There will be a take-home exam. Tentatively, the take-home exam will be assigned on Sep 18 and due on Sep 25. Late submission will not be accepted.

### In-Class Exam

There will be an open book/note in-class exam. This exam is tentatively scheduled on Oct 23.

### Final Project

The project is done in a group of three to four students. You address some questions that interest you with a statistical method(s) that you learn in this course and possibly other courses. Examples of the topics include psychology, sociology, natural science, medicine, public policy, sports, law, etc., but will need my approval. Detail will be discussed during the semester. Some milestones are below:

- Appointment with Instructor to discuss the project (2 points)
- Project proposal (5 points): due on Oct 2
- Preliminary results (5 points): due on Nov 18
- Presentation (5 points): 25 mins including Q&A on Dec 2 and 4
- Peer-evaluation (3 points): each group evaluate other groups’ presentations; due on Dec 6
- Final report (5 points): due on Dec 13

*Last updated: Fall 2019*

**STAT 435: Industrial Statistics**

## STAT435

### Instructor

David J. Edwards, Ph.D.

### Prerequisite(s)

STAT 309 and either STAT 305 or STAT 314, or equivalent, or permission of instructor

### Required Text

Introduction to Statistical Quality Control, 7th edition, by Douglas Montgomery

### Software

We will make extensive use of JMP Statistical Software Version 14. The software can be downloaded for free at VCU's Technology Services website.

### Homework

Homework will be assigned and collected on a regular basis. You may work with others on homework assignments. However, your final write up must be your own work and reflect your understanding of the material.

### Exams

Two midterm exams will be given during the semester. They will be announced at least one week in advance. All tests will be closed notes and closed book. I do not expect you to memorize formulas for this course; so formula sheets will be permitted during the tests. Given the nature of statistics, each test is necessarily cumulative in that the material learned early in the course will be needed for topics later in the course. There will be no make-up exams without prior permission of the instructor.

### Grading Policy

- Homework: 25%
- Exam 1: 25%
- Exam 2: 25%
- Final Exam: 25%

### Tentative Outline and Readings

- Introduction to Quality Improvement – Montgomery Chapter 1
- Tools for Process Study – Montgomery Chapter 5
- Introduction to Control Charts
- Flowcharts, Pareto Diagrams, Cause and Effect Diagrams
- Control Charts for Attributes Data – Montgomery Chapter 7
- p and np charts
- c and u charts
- Control Charts for Variables Data – Montgomery Chapter 6
- Variability and Location – R and Xbar charts, R and S charts
- Moving Range and Individuals charts
- Process and Measurement Capability Analysis – Montgomery Chapter 8
- Capability ratios
- Measurement studies
- Subgrouping and Components of Variation – Notes
- Introduction to Design of Experiments – Montgomery Chapter 13
- Two-level factorial experiments
- Fractional factorial experiments
- Introduction to Response Surface Methodology – Montgomery Chapter 14
- Sequential experimentation
- Second-order experimental designs
- Process optimization
- Additional Topics (as time allows) – Montgomery Chapters 9 and 11
- CUSUM and EWMA charts
- Multivariate process control

### Attendance Policy

Students are expected to attend every class meeting and to arrive to class on time. Class attendance and participation are essential in the learning process. It is difficult, if not almost impossible, to do well without practicing regular attendance.

### Course Objectives/Outcomes

At the end of the course, students will be expected to:

- Have an understanding of variability and its impact on quality control/process improvement
- Differentiate between common and special causes of variation
- Understand the philosophy of industrial statistics
- Create and interpret common tools for process study including process flowcharts, cause/effect diagrams, and Pareto plots
- Construct and interpret control charts for attributes data: p, np, c, and u charts
- Construct and interpret control charts for variables data: Xbar and R/S charts, moving range and individuals charts
- Understand how to quantify process capability
- Understand process components contributing to total variation
- Compute and interpret components of variation
- Understand the role of design of experiments in quality control/process improvement
- Construct and analyze designed experiments commonly used in industry: Two-level factorial and fractional factorial designs
- Understand the nature of sequential design of experiments for process optimization
- Analyze second-order experiments for process optimization

*Last updated: Fall 2018*

**STAT 441: Applied Statistics for Engineers and Scientists**

## STAT441

### Instructor

Qin Wang, Ph.D.

### Prerequisite(s)

Math 200-201 or equivalent. The ability to do calculus is necessary for this course.

### Required Text

Statistics for Engineering and the Sciences (5th edition) by William Mendenhall and Terry Sincich

### Homework

Homework will be assigned periodically and collected for grading. Discussion of these problems is encouraged, but you should construct and submit your own solution. All homework assignments are due at the beginning of class on the assigned due date, unless otherwise specified. Only hard copies of homework assignments will be accepted. No late assignments are permitted.

### Software

We will use statistical software in this class so we can look at real data—not all calculations can be done by hand. You can use any statistical software you like, so long as your homework solutions are straightforward for the grader. Software I recommend: R (open source), Matlab (statistics toolbox), Minitab, SPSS, SAS and JMP. I will demonstrate examples in class with Microsoft Excel.

### Grading Policy

- Homework (5-7): 20%
- Midterm (4): 60%
- Final exam: 20%

### GradingScale

- 90-100: A
- 80-89.99: B
- 70-79.99: C
- 60-69.99: D
- 0-59.99: F

### Exams

There will be four in-class midterms and one in-class comprehensive final exam. Absolutely no make-up exams will be allowed unless a university-approved excuse is provided. When possible, excuses should be provided at least two weeks in advance. More information will be provided about the exams later in the course.

All tests will be closed notes and closed book. I do not expect you to memorize formulas for this course; so a 1-page formula sheet will be permitted during the tests. Given the nature of statistics, each midterm is necessarily cumulative in that the material learned early in the course will be needed for topics later in the course. The final exam will be comprehensive, including all materials covered in this semester.

### Tentative Course Outline and Readings

- Introduction (1 week)
- Chapter 1- Sections 1.1-1.3

- Graphical and Descriptive Statistics (1 week)
- Chapter 2- Sections 2.1-2.8

- Probability, Random Variables, and Sampling Distributions (4 weeks)
- Chapter 3 – Sections 3.1-3.7
- Chapter 4 – Sections 4.1-4.6, 4.10
- Chapter 5 – Sections 5.1-5.6
- Chapter 6 – Sections 6.7-6.11

- Introduction to Inference: Estimation and Hypothesis Testing (3 weeks)
- Chapter 7 – Sections 7.1-7.11
- Chapter 8 – Sections 8.1-8.12

- Regression Analysis (Simple and Multiple) (4 weeks)
- Chapter 10 – Sections 10.1-10.11
- Chapter 11 – Sections 11.1-11.12

- Design of Experiments (1 week if time permits)
- Chapter 13 – Sections 13.1-13.5
- Chapter 14 – Sections 14.1-14.5, 14.8-14.9

- Industrial Statistics and Reliability (1 week if time permits)
- Chapter 16 – Sections 16.1-16.7
- Chapter 17 – Sections 17.1-17.7

*Last updated: Fall 2015*

**STAT 443: Regression**

## STAT443

### Instructor

Edward Boone

### Prerequisite(s)

STAT 314 and STAT 321. Completion of MATH 310 is strongly recommended. If you do not feel comfortable with the concepts and techniques from this andits prerequisite courses this course may be challenging.

### Required Text

Kutner, Nachtsheim, Neter, and Wasserman (2004) *Applied Linear Regression Models*,*Fourth Edition*, McGraw Hill/Irwin. ISBN-13: 978-0073014661

### Project

The project will involve the analysis of real world data in which linear or non-linear regressionanalysis is appropriate and will give the details of the analysis used. The dataset must containat least eight predictors and one response. The project report will be single spaced typed with 1inch margins with appropriate tables and figures will be included in the technical report and correctly cross-referenced. The goal is for the student to learn not only how to complete a specific analysis but also how to correctly and clearly communicate the results and their implications.All equations should be created using publication quality software such as Mathtype or LaTeX,etc. The R code used to complete your analysis will be attached as an appendix to the report.The code should be well commented and in runnable form.

### Software

For the statistical analysis portion of this course only the R statistical software package may beused. All code should be well commented and in runnable form.

### Grading Policy

The final grade will be comprised of weekly homework, two tests, a final exam and a project.These will be weighted as follows:

- Homework: 30%
- Test 1: 15%
- Test 2: 15%
- Final exam: 25%
- Project: 15%

The course grade will be assigned using a scale no harsher than:

- A: 90+
- B: 80 - 89.9
- C: 70 - 79.9
- D: 60-69.9
- F: 59.9 - below

### Comments

Grades for the course or on any assignment are not negotiable. If you attempt to negotiatea grade, then you will forfeit any leniency that may be available later. Of course if youhave an error in grading then those issues will be address appropriately with no penalty.

Cell phones, text messages and beepers should be turned off while in the classroom. Repeated offenses could result in a one letter reduction in course grade. If your cell phonemakes a sound during a test or exam the student will fail the course.

Responsible use of computers is required. If a student uses the computer inappropriatelythey will be asked to leave the class for the remainder of the class meeting period.

The VCU Honor System is in effect for all assignments, projects and examinations for thiscourse. Students may not work together on any assignment.

Any accommodations that need to be made for religious observances should be communicated to the instructor as soon as possible.

*Last updated: Fall 2015*

**STAT 445: Analyses of Dependent Data**

## STAT445

### Instructor

QiQi Lu, Ph.D.

### Textbook

*Applied Time Series Analysis*, by Wayne A. Woodward, Henry L. Gray,and Alan C. Elliott, 2012, CRC Press.

### References

*Time Series Analysis: with Applications in R, 2nd edition*, by Jonathan D. Cryerand Kung-Sik Chan, 2008, Springer.

*Time Series Analysis and its Applications, 2nd edition*, by Robert H. Shumway andDavid S. Stoffer, 2006, Springer.

*Time Series: Theory and Methods, 2nd edition*, by Peter J. Brockwell and RichardA. Davis, 1991, Springer.

*Introduction to Time Series and Forecasting, 2nd edition*, by Peter J. Brockwelland Richard A. Davis, 2002, Springer.

### Topics

- Introduction
- Stationary processes
- ARMA models
- Nonstationary models
- Forecasting, parameter estimation, and model diagnostics

### Software

R, a free software environment for statistical computing and graphics.No prior knowledge of R is required.

### Grading Policy

- Assignments: 30%
- Exam 1: 20%
- Exam 2: 20%
- Final exam: 30%

### Assignments

- Assignments will be made as lecture units are completed.
- You must show your work (when possible) in order to receive ANY credit.

### Exams

- Exam dates will be announced one week in advance.
- Each exam is closed-book and closed-notes.
- You must show your work (when possible) in order to receive ANY credit.

*Last updated: Spring 2015*

**STAT 475: Time Series Analysis**

## STAT475

### Instructor

Edward Boone, Ph.D.

### Course Description

Introduction to the modeling of univariate time series data. Topics include simple and exponential moving averages, Brown's double exponential smoothing, Holt-Winters model, autocorrelation, partial autocorrelation, autoregressive integrated moving average models, seasonalautoregressive moving average models, harmonic analysis and time series regression. Studentswill use modern statistical software to perform these analyses.

### Required Text

Cryer JD and Chan K-S (2008). *Time Series Analysis with Applications in R, Second**Edition*, Springer. ISBN-13: 9780387759586

### Prerequisite

Prerequisites: STAT 321 and either STAT 305 or STAT 314. Completion of STAT 421 isstrongly recommended. If you do not feel comfortable with the concepts and techniquesfrom this and its prerequisite courses this course may be challenging.

### Software

For this course we will use a variety of software such as MS Excel and R statistical Software.

### Grading Policy

The final grade will be comprised of weekly homework, two tests, a final exam and a project.These will be weighted as follows:

- Homework: 30%
- Test 1: 15%
- Test 2: 15%
- Final exam: 25%
- Project: 15%

The course grade will be assigned using a scale no harsher than:

- A: 90%+
- B: 80-89.9%
- C: 70-79.9%
- D: 60-69.9%
- F: 59.9%-

### Project

The project will involve the analysis of real world data in which univariate time series analysisis appropriate and will give the details of the analysis used. The project report will be single-spaced typed with 1 inch margins with appropriate tables and figures will be included in thetechnical report and correctly cross-referenced. The goal is for the student to learn not only howto complete a specific analysis, but also how to correctly and clearly communicate the resultsand their implications. All equations should be created using publication quality software suchas Mathtype or LaTeX, etc. The R code used to complete your analysis will be attached as anappendix to the report. The code should be well-commented and in runnable form.

### Comments

Grades for the course or on any assignment are not negotiable. If you attempt to negotiate a grade, then you will forfeit any leniency that may be available later. Of course if you have an error in grading then those issues will be address appropriately with no penalty.

Cell phones, text messages and beepers should be turned off while in the classroom. Repeated offenses could result in a one letter reduction in course grade. If you cell phone makes a sound during a test or exam the student will fail the course.

Responsible use of computers is required. If a student uses the computer inappropriately they will be asked to leave the class for the remainder of the class meeting period.

The VCU Honor System is in effect for all assignments, projects and examinations for this course. Students may not work together on any assignment.

Any accommodations that need to be made for religious observances should be communicated to the instructor as soon as possible.

*Last updated: Spring 2016*

**STAT 508: Introduction to Social Statistics**

## STAT508

### Instructor

Mita Basu

### Required Text

*Statistics: A Gentle Introduction*by Frederick L. Coolidge, 3rd edition; Sage publications

### Optional References

*Statistical Methods for the Social Sciences*by Alan Agresti and Barbara Finlay, 3rd edition, 1997*Statistics: A Guide to the Unknown*by Roxy Peck,George Casella, George Cobb, Roger Hoerl, Deborah Nolan,Robert Starbuck, Hal Stern

### Course Objective

To gain an understanding and working knowledge of the fundamental concepts of statistical methods, including the summary and description of data, analysis of data, and the use of statistical information as an aid in decision making. To recognize appropriate applications of these statistical methods, to perform the analysis, to explain the results, and to evaluate the findings prepared by others. To use computers and statistical software for data analysis and for preparing written reports that incorporate statistical findings.

### Calculator

You should have a calculator that you know how to use and should bring this to class regularly. Instructions for using TI-83, TI-83 Plus, TI-84 and TI-84 Plus calculators are posted on Blackboard, but other calculators are acceptable as well. You will not be allowed to use cell phones on any graded assignment (tests or final exam). Sharing of calculators will not be allowed on any graded assignment and will be considered an Honors violation if observed. The department has a limited number of calculators that can be rented for the semester for $10.00. See Samantha Powell in Harris 4144 if you are interested.

### Software

The class will introduce you to the Windows version of SPSS. The current version is 25.Please see separate handout posted under Course documents about more information on SPSS.Also, I will be giving you handouts in class with SPSS examples from time to time. You can also use the VCU online help to learn SPSS.

### Grading Policy

- Test 1: 10%
- Test 2: 20%
- Test 3: 20%
- Final exam: 30%
- Graded quiz: 20%

In addition, class participation will be considered in assigning a semester grade. Make-up tests are not given except in highly unusual circumstances, and only when arrangements are made with the instructor prior to the scheduled test date. Take home quizzes are due at the beginning of class on the due date. Quizzes may not be completed late. Late quizzes will not be graded. However, one of the lowest quiz grades will be dropped in determining the quiz average.

Your course letter grade will be based on the ten point scale:

- A: 90 or above
- B: 80 - 89.99
- C: 70 - 79.99
- D: 60 - 69.99
- F: below 60

### Topics/Schedule

Week | Topic |
---|---|

August 22 | Introduction, Syllabus, Start with Chapter 1-Basic terminologies, Types of bias/Introduction to Sampling |

August 29 | Chapter 1 continued.- Sampling/Design of Experiments |

September 5 | Chapter 1 continued; Start with Chapter 2-Descriptive Statistics |

September 12 | Chapter 2 continued; Start with Chapter 3 -Numerical summaries- Measures of Central location and Spread |

September 19 | Test 1 review; Chapter 3 continued |

September 26 | First Half: Test 1(covers chapters 1 and 2); Second half- Chapter 3 SPSS lab; Start with Chapter 4-part 1 –Normal distributions |

October 3 | Chapter 4 (part 1 continued) |

October 10 | Chapter 4 (Part 1 continued); Start with Chapter 4 -part 2- Sampling distributions of sample mean and sample proportion. |

October 17 | Test 2 review; Chapter 4-part 2 continued. |

October 24 | First Half: Test 2(covers chapters 3 and 4 part 1 only); Second half: Chapter 4-part 2 continued |

October 31 | Chapter 4 (Part 2 continued); Start with Chapter 5- Inferential Statistics-Confidence intervals and tests of significance for a single population |

November 7 | Chapter 5- continued Inferential Statistics-Confidence intervals and tests of significance for a single population, t distributions |

November 14 | Chapter 5/SPSS lab continued; Test 3 review |

November 21 | First Half: Test 3 (covers chapter 4 Part 2 and Chapter 5); Second half: Start with Chapter 6-Correlation and Regression |

November 28 | No class - Thanksgiving Break |

December 5 | Chapter 6 continued; Final Exam review |

December 12 | Cumulative Final Exam: 4-6:50 pm |

### Requirements

Attendance, daily reading and homework, and active participation in class are required to master the material. Reading and homework will be assigned for each class meeting. For each class meeting, you should have read the material, attempted the assigned exercises, and be prepared to participate in the class discussion. Take home quizzes will be assigned and they should be turned in on the due date for a grade. Working the practice problems identified on the handouts for each class meeting is critical to mastering the material.

### Attendance Policy

Attendance will be checked at the beginning of each class. You should be seated and ready to begin class at the scheduled starting time. Late arrivals should be avoided, but if it occurs, please be respectful of others and be seated quickly to minimize interruptions. See the instructor after class to confirm your attendance. Other disruptions that should be avoided include getting up and leaving the room during class, talking during lectures, etc. Please turn off cell phones or keep them in silent mode during lectures and labs. A short break will be given at about the midpoint of each class session.

*Last updated: Fall 2019*

**STAT 514: Mathematical Statistics II**

## STAT514

### Instructor

QiQi Lu, Ph.D.

### Prerequisite(s)

Math 307 (Multivariate Calculus) and Stat 513 (Math Stat I)

### Required Text

*Statistical Inference*, 2nd edition, by George Casella and Roger L. Berger,2002, Duxbury.

### Grading

- Assignments: 30%
- Exam 1: 20%
- Exam 2: 20%
- Final exam: 30%

### Topics

- Properties of a Random Sample (Chapter 5)
- Principles of Data Reduction (Chapter 6)
- Point Estimation (Chapter 7)
- Hypothesis Testing (Chapter 8)
- Interval Estimation (Chapter 9)

### Assignments

- Homework will be assigned nearly every week.
- You must show your work (when possible) in order to receive ANY credit.

### Exams

- Exam dates will be announced one week in advance.
- Each exam is closed-book and closed-notes.
- You must show your work (when possible) in order to receive ANY credit.

*Last updated: Spring 2015*

**STAT 543: Statistical Methods I**

## STAT 543

### Instructor

Hossein Moradi Rekabdarkolaee

### Prerequisite(s)

Graduate student standing and or permission of the instructor. This course is quite intense and assumes the student has an adequate mathematical preparation including first year Calculus. If you do not feel comfortable with the concepts from Calculus you may find this course challenging.

### Texts

*Statistical Research Methods A Guide for Non-Statisticians*by Sabo, Roy and Boone, Edward*An Introduction to Statistical Methods and Data Analysis*by R. Lyman Ott and Micheal T. Longnecker*Learning Statistics Using R*by Randall E. Schumacker. SAGE Publications.*Introductory Statistics with R*by Peter Dalgaard. Springer New York.

### Course Description

Basic concepts and techniques of statistical methods, including: the collection and display of information, data analysis and statistical measures; variation, sampling and sampling distributions; point estimation, confidence intervals and tests of hypotheses for one and two sample problems; principles of one-factor experimental design, one-way analysis of variance and multiple comparisons; correlation and simple linear regression analysis; contingency tables and tests for goodness of fit. Students may not receive degree credit for both STAT 441/541 and STAT 543. STAT 543 is not applicable toward the M.S. degree in mathematical sciences or the M.S. degree in computer science.

### Software

This course will use the R statistical software package exclusively. No other statistical software may be used on any assignment. Any assignment that uses any other package will be given no credit.

### Grading Policy

Grades for the course or on any assignment are not negotiable. If you attempt to negotiate a grade then you will receive no credit on the item or the entire assignment. Of course if you have an error in grading then those issues will be address appropriately with no penalty.

The final grade will be comprised of weekly homework, midterm and a final exam. These will be weighted as follows:

- Homework:40%
- Midterm:30%
- Final:30%

The course grade will be assigned using a scale no harsher than:

- A:90% +
- B:80-89.99%
- C:70-79.99%
- D:60-69.99%
- F:59.99% -

### Homework

Homework will be given on a regular basis and must be turned in on time before the beginning of class. No late homework will be accepted. No homework scores will be dropped from consideration. All homework assignments must be hard copies single-sided and stapled unless directed otherwise. For computer related homework, only relevant output should be included and it should be well-labeled and identified. Computer output alone constitutes no credit. Any Blackboard submission not in pdf format will receive a grade of zero.

*Last updated: Fall 2015*

**STAT 546: Linear Models**

## STAT 546

### Instructor

David J. Edwards, Ph.D.

### Prerequisite(s)

STAT 513 (or equivalent) and one applied statistics course, or permission of instructor

### Required Text

*Linear Models in Statistics, 2nd edition*, by Alvin C. Rencher and G. Bruce Schaalje

### Supplementary Reading

A good working knowledge of matrix algebra is vital to the understanding of linear models theory. We will spend some time with this in chapter 2, but depending on your background and comfort level, you may wish to look at other sources.

*Matrix Algebra from a Statistician’s Perspective*, by David Harville*Introduction to Matrices with Applications in Statistics*, by Franklin Graybill*Matrix Algebra Useful for Statistics*, by Shayle Searle*A Matrix Handbook for Statisticians*, by George Seber

### Catalog Description

A study of the theory underlying the general linear model and general linear hypothesis. Topics include the general linear model for quantitative responses (including multiple regression, analysis of variance, and analysis of covariance), binomial regression models for binary data (including logistic regression and probit models) and Poisson regression models for count data (including log-linear models for contingency tables and hazard models for survival data).

### Software

We will not do very much computing as this is primarily a theory course. However, we will occasionally use MATLAB and/or R.

### GradingScale

- A: 90-100
- B: 80-89.99
- C: 70-79.99
- D: 60-69.99
- F: <60

### Tentative Outline

Topics | Textbook Readings |
---|---|

Introduction | Chapter 1 |

Review of Matrix Algebra | Chapter 2 |

Random Vectors and Matrices | Chapter 3 |

Multivariate Normal Distribution | Chapter 4 (sections 1-4) |

Distributions of Quadratic Forms | Chapter 5 |

Regression Models | |

Simple Linear Regression | Chapter 6 |

Estimation in Multiple Regression | Chapter 7 (sections 1-9) |

Inference for Multiple Regression | Chapter 8 |

Model Validation and Diagnostics | Chapter 9 |

ANOVA Models | |

Understanding Non-Full Rank Models | Chapter 12 |

One-way ANOVA | Chapter 13 |

Two-way ANOVA | Chapter 14 |

Generalized Linear Models (as time allows) | |

Logistic Regression | Chapter 18 + supplemental material |

Poisson Regression | Chapter 18 + supplemental material |

### Homework

Homework will be assigned and collected on a regular basis. You may work with others on homework assignments. However, your final write up must be your own work and reflect your understanding of the material.

*Last updated: Spring 2019*

**STAT 608: Statistics for Social Research**

## STAT608

### Instructor

Mita Basu, Ph.D.

### Prerequisite(s)

Completion of STAT/SOCY 508 or SOCY 214

### Required Text

*Statistics: A Gentle Introduction*,by Frederick L. Coolidge,3rd edition, Sage publications

### Software

The class will introduce you to the Windows version of SPSS. More details will be given on the first day of class.

I expect students to be familiar with email and text processing software (e.g. WORD).I may assign some computer work outside of class. You can use a VCU computer to do these assignments. Your school or department may also have a computer lab with SPSS available to graduate students. There are a lot of books on SPSS available in the market. "Doing Data Analysis with SPSS" by Carver and Nash is a good book that you could refer to. I will be giving you handouts from time to time.

### Grading Policy

- Test 1: 10%
- Test 2: 10%
- Test 3: 10%
- Final exam: 30%
- Graded quiz: 20%
- Project: 20%

In addition, class participation will be considered in assigning a semester grade. Make-up tests are not given except in highly unusual circumstances, and only when arrangements are made with the instructor prior to the scheduled test date.

Your course letter grade will be based on the ten point scale:

- 90 or above: A
- 80 – 89.99: B
- 70 – 79.99: C
- 60 – 69.99: D
- Below 60: F

### Assignments

Take home quizzes will be assigned and they should be turned in on the due date for a grade. Take home quizzes are due at the beginning of class on the due date. These assignments must be completed so that they are legible (if I can’t read your work it will not be graded). If you have difficulty with any of the homework, I will be more than happy to work with you. Quizzes may not be completed late. Late quizzes will not be graded. However, one of the lowest grades will be dropped in determining the quiz average.

### Attendance Policy

Attendance will be checked at the beginning of each class. You should be seated and ready to begin class at the scheduled starting time. Late arrivals should be avoided, but if it occurs, please be respectful of others and be seated quickly to minimize interruptions. See the instructor after class to confirm your attendance. Disruptions that should be avoided include getting up and leaving the room during class, talking during lectures, etc. Please turn off cell phones or keep them in vibrate mode during lectures and labs. A short break will be given at about the midpoint of each class session.

*Last updated: Spring 2015*

**STAT 613: Stochastic Processes**

## STAT 613

### Instructor

Cheng Ly, Ph.D.

### Required Text

*Introduction to Probability Models*, by Ross. 10th edition. ISBN-10: 0123756863, ISBN-13:978-0123756862. Publisher: Academic Press (Elsevier).

### Calculator

Calculators are allowed on homework and exams (TI-89 or below), however, you must show all ofyour work to receive credit.

### Grading Policy

- Homework: 40%
- Midterm: 30%
- Final exam: 30%

Letter grade assignments will be no harsher than the 10% scale (i.e., >90% is a guaranteed A).Homework will be assigned and graded about every few weeks.

### Topics/Schedule

- Chapter 1: Introduction to probability theory [0.5 weeks]
- Chapter 2: Random Variables [2 weeks]
- Chapter 3: Conditional Probability and Conditional Expectation [2 weeks]
- Chapter 4: Markov Chains [3 weeks]
- Chapter 5: The Exponential Distribution and Poisson Processes [3 weeks]
- Chapter 6: Continuous-Time Markov Chains [1 week]
- Chapter 7 and/or 8 [1 week]

### Exam Policy

NO MAKE-UP exams unless you have an emergency or legitimate excuse. In the event of an emergency, you must notify me before the exam and provide evidence.You must have a legitimate excuse otherwise you will receive a 0 on the exam.

*Last updated: Spring 2015*

**STAT 621: Nonparametric Statistical Methods**

## STAT 621

### Instructor

Anh T. Bui, Ph.D.

### Prerequisite(s)

Probability and statistical inference such as STAT 513, STAT 546 or with my permission. No prior knowledge of nonparametric statistics is required.

### Required Text

There will be no required textbook in this course. The below references are optional:

- Applied Nonparametric Statistical Methods, Fourth Edition, Peter Sprent and Nigel C. Smeeton, Chapman & Hall/CRC.
*An introductory book about nonparametric statistics with many examples.* - Nonparametric Statistical Inference, Fifth Edition, Jean D. Gibbons and Subhabrata Chakraborti, Chapman & Hall/CRC.
*A more advanced book about nonparametric statistics that focuses more on the methodological aspects.* - The Elements of Statistical Learning, Second Edition, Trevor Hastie, Robert Tibshirani, and Jerome Friedman, Springer.
*An advanced book for regression and classification. There is also a more introductory book from the same authors.* - Multivariate Density Estimation, Second Edition, David W. Scott, Wiley.
*An advanced book for nonparametric density estimation methods.*

### Homework

This course has five homework assignments in total. Homework assignments are due at the beginning of the classes on the due dates. Late submission will not be accepted. You are encouraged to discuss on homework assignments, but you must write your own solutions.

### Presentation

About seven topics in nonparametric statistics will be assigned to students to present. Tentatively, the presentations will take place from Weeks 3 to 8. Submit your slides on Blackboard on thesame day with and before the presentation. Evaluation will be based on the quality of both your slidesand talk.

### In-Class Exam

There will be one in-class exam, tentatively scheduled on Oct 24 (Thursday). This willbe an open book and note exam.

### Final Project

The project is done individually or in a group of two students, depending on the numberof students. There are two types of project you can select:

- Criticize a research paper about its development/application of nonparametric statistical methods.
- Apply/develop nonparametric statistical methods for your research problem.

### Grading Policy

Homework (25%), presentation (25%), in-class exam (25%), final project (25%), and class participation.

*Last updated: Fall 2019*

**STAT 623: Discrete Multivariate Analysis**

## STAT 623

### Instructor

Qin Wang, Ph.D.

### Prerequisite(s)

Probability and Statistical methods (at least STAT 541 or equivalent). Much of this coursedeals with extensions of regression modeling to handle categorical response variables, sostudents should be comfortable with multiple regression modeling, including the use ofdummy variables for incorporating categorical predictors in a model, and should have hadpractice using statistical software for regression and ANOVA.

### Textbook

*An Introduction to Categorical Data Analysis (2nd edition)* by Alan Agresti, Wiley, 2007.

### Software

- We will use statistical software in this class so we can look at real data - not all calculationscan be done by hand
- Software I recommend: R (open source) and SAS. I will provide resources for you withSAS

### Grading Policy

- Homework: 40%
- Mid-term: 30%
- Final Exam: 30%

The homework grades will reflect completeness and timeliness. You are encouraged towork together to master these exercises, but you should construct and submit your own solution.Tests are graded for correctness, and must be your own individual work.

### Grading Scale

- A: 90-100
- B: 80-90
- C: 70-80
- D: 60-70
- F: < 60

### Topics/Schedule

- Introduction to categorical data (chapter 1)
- Description and inference for binomial and multinomial observations using roportionsand odds ratios (chapter 1-2)
- Classical Analysis of Contingency Tables (chapter 2)
- Generalized linear models for discrete data (chapter 3)
- Logistic regression for binary responses; (chapter 4 and 5)
- Multi-category logit models for nominal and ordinal responses (chapter 6)
- Loglinear models (chapter 7)
- Models for matched pairs (chapter 8 if time permits)

### How to be Successful in the Course

- Read the corresponding sections of the textbook as we cover the course material
- Understand all the material in the course lecture notes
- Understand and re-run all program codes and calculations
- Complete all homework assignments and take all exams

### Guidelines

- Attend all classes and arrive at class on time. If you miss class, you are responsible forany material covered in class that you missed, including information not included in yourtextbook. Please talk with me if something prevents you from arriving to class on time.
- Regularly check your email and Canvas (at least every other day) for announcementsand assignments.
- While I check my own email frequently during the week and at least once on weekends,a situation may arise where this is not possible. Do not wait until the last day before anassignment is due to contact me if you have questions.
- The course syllabus is a general plan for the course; deviations announced to the class bythe instructor may be necessary.

*Last updated: Spring 2015*

**STAT 641: Applied Data Analysis**

## STAT 641

### Instructor

Yanjun Qian, Ph.D.

### Prerequisite(s)

Math 200-201 or equivalent, and Stat 212 or equivalent. The ability to do calculus is necessary for this course. Basic knowledge of probability, statistical inference, and statistical modeling is required.

### Textbook

*Statistical Analysis and Data Display, An Intermediate Course with Examples in R, 2nd edition*, Heiberger and Holland, Springer 2015.(Free access to the eBook of this textbook through VCU Library)

### Reference Book

*Statistics for Engineering and the Sciences* by William Mendenhall and Terry Sincich, Pearson (5th edition, 2007) / CRC Press (6th edition, 2016).

### Software

We will use statistical software in this class so we can look at real data—not all calculations can be done by hand. Software I recommend: R (open source), MATLAB (statistics toolbox), Minitab, SPSS, SAS and JMP. I will demonstrate examples in class with R.

### Course Objectives

You are expected to

- Summarize data using descriptive statistics
- Understand probability distributions and the Normal distribution
- Understand sample statistics and statistical inference
- Construct point estimate, confidence interval and perform hypothesis testing
- Perform linear regression and analysis of variance
- Understand bivariate statistics for discrete data
- Understand nonparametric statistics

### Grading Policy

- In-class quizzes (6-8) (20%)
- Exam 1 and 2 (50%)
- Exam 3 (30%)
- Bonus project (5%)

All assessment grades will count towards the final course grade.

- A: 90-100
- B: 80-89.99
- C: 70-79.99
- D: 60-69.99
- F: 0-59.99

### Homework

Homework will be assigned periodically but may not be collected for grading. Popup quizzes related to homework questions will be assigned during the class and graded.

### Exams

There will be two in-class exams and one in-class comprehensive Exam 3. Absolutely no make-up exams will be allowed unless a university-approved excuse is provided. Whenever possible, excuses should be provided at least two weeks in advance. More information will be provided about the exams later in the course.

All tests will be closed notes and closed book. I do not expect you to memorize formulas for this course; so, a 1-page formula sheet will be permitted during the tests. Given the nature of Statistics, each midterm is necessarily cumulative in that the material learned early in the course will be needed for topics later in the course. The final exam will be comprehensive, including all materials covered in this semester.

*Last updated: Fall 2019*

**STAT 642: Design and Analysis of Experiments I**

## STAT 642

### Instructor

David J. Edwards, Ph.D.

### Prerequisite(s)

Graduate standing in mathematical sciences or systems modeling and analysis, or permission of instructor; it is recommended that students have taken at least STAT 641 or BIOS 553 or equivalent.

### Required Text

*Design and Analysis of Experiments, 9th edition*, by Douglas C. Montgomery

### Homeword

Homework will be assigned and collected on a regular basis. You may work with others on homework assignments. However, your final write up must be your own work and reflect your understanding of the material.

### Software

We will make extensive use of JMP Statistical Software Version 14. The software can be downloaded for free from the VCU Technology Services website.

### Grading Policy

- Homework and project: 25%
- Exam 1: 25%
- Exam 2: 25%
- Final exam : 25%

90-100 (A), 80-89.99 (B), 70-79.99 (C), 60-69.99 (D), <60 (F)

### Topics/Schedule

Tentative Outline | Readings in Montgomery |
---|---|

Basic Principles of DOE | Chapters 1 & 2 |

Single Factor Experiments (Fixed and Random) | Chapter 3 (Sections 1, 2, 3, 5, 9) Chapter 10 (Section 8) Chapter 13 (Section 1) |

Analysis Methods (Model Adequacy Checking, Transformations) | Chapter 3 (Section 4) Chapter 15 (Section 1.1) |

Introduction to Factorial Designs | Chapter 5 (Sections 1-5) |

Increasing Precision (Complete and Incomplete Block Designs, Latin Squares, Analysis of Covariance) | Chapter 4 (Sections 1, 2, 4) Chapter 5 (Section 6) Chapter 15 (Section 3) |

Two-Level Factorial Designs | Chapter 6 |

Blocking Two-Level Designs | Chapter 7 |

Two-Level Fractional Factorial Designs | Chapter 8 Chapter 9 (Section 5) |

Response Surface Methods | Chapter 11 |

Random and Nested Factors | Chapter 13 (Sections 1, 2, 6) Chapter 14 (Sections 1, 2) |

Complex Experiments (Mixed Models) | Chapter 13 (Sections 3, 4, 5, 6) Chapter 14 (Section 3) |

Split-Plot Experiments | Chapter 14 (Sections 4, 5) |

Further Topics as Time Allows (Nonregular Designs, Optimal Design, etc.) | Chapter 11 (Section 4.4, 5) Chapter 12 |

*Last updated: Spring 2019*

**STAT 643: Applied Linear Regression**

## STAT 643

### Instructor

D'Arcy Mays, Ph.D.

### Prerequisite(s)

Calculus [MATH 200-201 or equivalent]; Introductory Statistics [STAT 212 or equivalent]; and Linear Algebra [MATH 310 or equivalent]

### Required Text

*Classical and Modern Regression With Applications, 2nd edition*, by Raymond H. Myers (currently out of print; PDF’s of chapters posted on Canvas, or you can purchase a copy from an online source; we have a few departmental copies that can be borrowed.)

### Calculator

A calculator that you know how to use

### Software

The course will also use the SAS statistical software package. Previous knowledge of SAS is not necessary.

### Grading Policy

- Homework: 25%
- Project: 15%
- Test 1: 20%
- Test 2: 20%
- Test 3 (Final Exam): 20%

### Homework

Homework assignments will be made and collected on a regular basis. You may work together on the homework, but what you turn in should represent your understanding of the problems. Late homework will not be accepted unless permission to turn the homework in late is granted in advance.

### Examinations

The tests and final exam will be closed book, closed notes, in class exams. Test 1 will cover sections I through IV, test 2 will cover sections V through VII, and the final exam will cover sections VIII through XIII. Make-up tests will only be given in documentable emergencies. The tests and final exam are subject to the VCU Honor System.

### Project

The project will consist of three stages. In the first stage the student will identify a situation in which linear regression procedures are appropriate. This includes identifying the background for the situation being modeled, identifying the response variable that is going to be measured, and identifying the independent variables that are going to be measured. This information should be typed into a “project summary” and submitted by Thursday, September 21. The second stage involves collecting data for each of the variables and adding this data to your “project summary”. The revised project summary must be submitted as a Microsoft Word attachment to an email message to the instructor by Tuesday, October 24. On Tuesday, November 1 the third stage will begin when each student will randomly select another student’s “project summary” and will spend the next month analyzing the data. During the analysis stage, the student who prepared the “project summary” becomes a consultant and is expected to answer questions asked of them by the analyst. Each analyst will prepare an “analyst summary” that details the steps that he or she completed, why each step was done, and what was concluded at each step. The “analyst summary” will also include a recommendation as to the final model to use, and will reference all communication made with the consultant. The analyst summary is due on Tuesday, December 5.

*Last updated: Fall 2017*

**STAT 645: Bayesian Decision Theory**

## STAT645

### Instructor

Edward Boone, Ph.D.

### Prerequisite(s)

Prerequisite: STAT 513, and STAT 514. If you do not feel comfortable with the concepts andtechniques from these courses this course may be challenging.

### Required Text

Berger, J.O. (1985) Statistical Decision Theory and Bayesian Analysis, Second Edition. Springer,New York. ISBN-13: 978-1441930743

### Software

This course will use the R statistical software package exclusively. No other statistical softwaremay be used on any assignment. Any assignment that uses any other package will be given nocredit.

### Grading Policy

- Homework: 40%
- Exam 1: 20%
- Exam 2: 20%
- Final Exam: 20%

The course grade will be assigned using a scale no harsher than:

- A: 90%+
- B: 80- 89.9%
- C: 70- 79.9%
- D: 60- 69.9%
- F: 59.9% -

Grades for the course or on any assignment are not negotiable. If you attempt to *negotiate* agrade, then you will forfeit any leniency that may be available later. Of course if you have an error in grading then those issues will be address appropriately with no penalty.

### Homework

Homework will be given on a regular basis and must be turned in on time before the beginningof class. No late homework will be accepted. No homework scores will be dropped from consideration. All homework assignments must be hard copies single-sided and stapled unlessdirected otherwise. For computer related homework, only relevant output should be includedand it should be well-labeled and identified. Computer output alone constitutes no credit.

*Last updated: Fall 2014*

**OPER/STAT 649: Statistical Quality Control**

## OPER/STAT 649

### Instructor

Yanjun Qian, Ph.D.

### Prerequisite(s)

- Linear Algebra or Matrix Algebra (MATH 310, or equivalent)
- Knowledge on hypothesis test and linear regression (STAT 310, or equivalent)

### Required Text

None. Class notes will be posted on the course website.

### Software

We will use in this class so we can look at real data—not all calculations can be done by hand. Software I recommend: Excel, MATLAB, R, SAS and Minitab. I will demonstrate examples in class with MATLAB or R.

### Grading Policy

- In-class quizzes (5-6): 10%
- In-class exams (4): 80%
- Course project: 10%

All assessment grades will count towards the final course grade.

### Grading Scale

- 90 – 100: A
- 80 – 89.99: B
- 70 – 79.99: C
- 60 – 69.99: D
- 0 – 59.99: F

### Topics

- Statistical background: confidence intervals and hypothesis tests
- Shewhart control chart: method and evaluation using ARL
- Control charts with memory: CUSUM and EWMA
- Control charts for attribute data
- Univariate analysis: risk adjustments
- Multivariate statistics
- Hotelling T2 charts
- Multivariate CUMSUM and EWMA
- Handling the high-dimension data
- Multivariate control charts for attribute data
- Time-space cluster detection: spatial-temporal scan statistics (optional)

### Exams

There will be four in-class exams. Absolutely no make-up exams will be allowed unless a university-approved excuse is provided. Whenever possible, excuses should be provided at least two weeks in advance. More information will be provided about the exams later in the course.

All tests will be closed notes and closed book. I do not expect you to memorize formulas for this course; so, a 1-page formula sheet will be permitted during the tests.

### Homework

Homework will be assigned periodically but may not be collected for grading. Popup quizzes related to homework questions will be assigned during the class and graded.

### Guidelines

- Attend all classes and arrive at class on time. If you miss class, you are responsible for any material covered in class that you missed, including information not included in your textbook. Please talk with me if something prevents you from arriving to class on time.
- Regularly check your email and Canvas (at least every other day) for announcements.
- Readings should be completed before class.
- While I check my own email frequently during the week and at least once on weekends, a situation may arise where this is not possible. Do not wait until the last day before an assignment is due to contact me if you have questions!
- I value integrity. Cheating in any form will not be tolerated. The documented policies of the department, college, and university related to academic integrity will be enforced. Any violation of these regulations, including acts of plagiarism or cheating, will be dealt with according to those policies.
- The course syllabus is a general plan for the course; deviations announced to the class by the instructor may be necessary.

*Last updated: Spring 2019*

**STAT 650: Design and Analysis of Response Surface Experiments**

## STAT 650

### Instructor

David J. Edwards, Ph.D.

### Prerequisite(s)

STAT 641 or STAT 642 or BIOS 553-554, or permission of the instructor

### Required Text

*Response Surface Methodology: Process and ProductOptimization Using Designed Experiments, Fourth Edition*, by Myers, Montgomery and Anderson-Cook; Wiley, 2016.

### Calculator

You should have a calculator that you know how to use and should bringthis to all tests and the final exam.

### Software

The course will use the SAS and JMP statistical software packages.

### Grading Policy

- Homework 25%
- Test 1: 20%
- Test 2: 20%
- Project: 15%
- Final Exam: 20%

Your course letter grade will be based on the ten point scale:

- A: 90 - 100+
- B: 80 - 89.99
- C: 70 - 79.99
- D: 60 - 69.99
- F: Below 60

### Homework

Homework assignments will be made and collected on a regular basis. You may work together on the homework, but what you turn in should represent your understanding of the problems. Late homework will not be accepted unless permission to turn the homework in late is granted in advance.

### Examinations

The tests and final exam will be given in class. Test 1 will likely cover sections I through IV; test 2 will likely cover sections V through IX; and the final exam will likely cover sections X through XIII. Make-up tests will only be given in documentable emergencies. The tests and final exam are subject to the VCU Honor System.

*Last updated: Fall 2017*

**STAT 675: Time Series Analysis I**

## STAT 675

### Instructor

QiQi Lu, Ph.D.

### References

*Time Series Analysis: with Applications in R, 2nd edition*, by Jonathan D. Cryerand Kung-Sik Chan, 2008, Springer.

*Time Series Analysis and its Applications, 2nd edition*, by Robert H. Shumway andDavid S. Stoffer, 2006, Springer.

*Time Series: Theory and Methods, 2nd edition*, by Peter J. Brockwell and RichardA. Davis, 1991, Springer.

*Introduction to Time Series and Forecasting, 2nd edition*, by Peter J. Brockwelland Richard A. Davis, 2002, Springer.

### Software

R — a free software environment for statistical computing and graphics.

### Grading Policy

- Assignments: 30%
- Exam 1: 20%
- Exam 2: 20%
- Final exam: 30%

### Grading Scale

A=[90, 100], B=[80, 90), C=[70, 80), D=[60, 70), F=[0, 60)

### Topics

- Introduction
- Stationary processes
- ARMA models
- ARIMA models
- Parameter estimation and model diagnostics
- Forecasting
- Seasonal models
- Time series regression models

### Assignments

Assignments will be made as lecture units are completed. You must show your work (when possible) in order to receive ANY credit.

### Exams

Exam dates will be announced one week in advance.Each exam is closed-book and closed-notes.Formula sheets made up by you are allowed.You must show your work (when possible) in order to receive ANY credit.

*Last updated: Fall 2015*

**STAT 742: Design and Analysis of Experiments II**

## STAT 742

### Instructor

David J. Edwards, Ph.D.

### Prerequisite(s)

STAT 642 or equivalent

### Textbooks

*Experiments: Planning, Analysis, and Optimization*by C.F. Jeff Wu and Michael Hamada, 2nd edition, 2009*A Comprehensive Guide to Factorial Two-Level Experimentation*, 2009, by Robert W. Mee*Optimal Design of Experiments*, 2011, by Peter Goos and Bradley Jones

### Software

JMP, SAS, R and/or MATLAB

### Grading Policy

- Homework: 40%
- Literature study: 10%
- Midterm: 25%
- Final: 25%

### Topics

- Two-Level Designs
- Regular Fractional Factorial Designs/Minimum Aberration
- Nonregular Designs and Orthogonal Arrays
- Sequential Experimentation
- Supersaturated Designs and Analysis

- Designs with More Levels and Response Surface Designs
- Definitive Screening Designs
- Response Surface Designs (orbits) and Ridge Analysis
- One-Step RSM
- Multiple Response Optimization
- Mixture Experiments

- Additional Topics
- Robust Parameter Design
- Optimal Experimental Design
- Partial Replication
- Computer Experiments
- Other topics of interest to the class

### Journal Article Reading/Summary/Discussion

10% of your grade will be determined based on article summaries and discussion for four recent articles in the design and analysis of experiments.

### Conditions on Source of Articles and Your Report

- You are free to select any journal article or case study on design or analysis of experiments from 2010-19
- You should read and report on at least one article from two of the following journals: Quality and Reliability Engineering International, Quality Engineering, Journal of Quality Technology, Technometrics
- Submit each choice to me for approval at least one week before the discussion date. I’ll let you know if the article is acceptable.

Your report (maximum of two typed pages) must contain:

- Article title and authors
- Journal name, date, and page numbers
- Your summary
- Your name

*Last updated: Fall 2019*

**STAT 745: Advanced Bayesian Statistics**

## STAT 745

### Instructor

Edward Boone, Ph.D.

### Prerequisite(s)

STAT 513, STAT 514 and STAT 645. If you do not feel comfortable with theconcepts and techniques from these courses this course may be challenging.

### Optional Texts

- Bernardo JM and Smith AFM (1994)
*Bayesian Theory*, Wiley, New York. - Gilks WR, Richarson S and Spiegelhalter DJ (1996)
*Markov Chain Monte Carlo in Practice*, Chapman & Hall/CRC, Boca Raton. - Albert J (2009)
*Bayesian Computation with R*, Springer, New York. - Lee PM (2012)
*Bayesian Statistics: An Introduction, Fourth Edition*, Wiley, West Sussex,UK.

### Homework

All assignments must be single-sided and stapled unless directed otherwise. Also, for computer based problems, only the relevant output should be included, and it should be well-labeledand identified. Computer output alone constitutes no credit. Often students forget that theoutput constitutes no credit and lose valuable points. Remember homework is worth 35% ofyour grade. Homework should be submitted before the beginning of class. Any assignmentsnot submitted before the beginning of class will not be graded and hence will be given no credit.For students who are submitting their homework from a distance be sure to have it in the Blackboard assignments by classtime.

### Project

The student will take a modern paper (no older than 5 years) concerning Bayesian statistics andreplicate the results in their paper and extend the paper via either theoretical development orsimulation study. The final report will be typed using LaTeX using the ims-template.tex format.html. The report should include an appropriate title, introduction, verification, conclusionssections. The final report will be no longer than 10 pages. All references must be in refereedjournals or texts and must be cited appropriately in the body of the text. Information fromwebsites, blogs etc are not permitted.

### Seminars

The student will give two seminars: one presenting the paper for their project andthe other presenting the extension of the paper. The first seminar must occurat least 4 weeks prior to the second.

### Grading Policy

Grades for the course or on any assignment are not negotiable. If you attempt to negotiate agrade, then you will forfeit any leniency that may be available later. Of course if you have anerror in grading then those issues will be address appropriately with no penalty.

The final grade will be comprised of homework, a project, and two seminars. These will beweighted as follows:

- Homework: 35%
- Project: 50%
- Seminar 1: 5%
- Seminar 2: 10%

The course grade will be assigned using a scale no harsher than:

- A: 90%+
- B: 80 - 89.9%
- C: 70 - 79.9%
- D: 60 - 69.9%
- F: 59.9%-

*Last updated: Spring 2015*

**STAT 744: Regression II**

## STAT 744

### Instructor

James Mays, Ph.D.

### Prerequisite(s)

STAT 643 (Applied Linear Regression), or equivalent

### Textbook and Course Notes

*Classical and Modern Regression With Applications, 2nd edition*, by Raymond H. Myers, 1990.NOTE: PDFs of the chapters of this text are available on the class website.

Course Notes packet (required) is available at Uptown Copy (Main Street, one block west of 7-11) (#16).

### Equipment

A calculator that you know how to use. The course will also use the SAS statistical software package. You may purchase your own PC Version, borrow installation disks to install the software, or use the Mathematical Sciences computer lab. Prior knowledge of SAS is not necessary, but is helpful.

### Grading Policy

A ten-point grading scale will be used. Your final average grade will be determined as follows:

- Homework: 40%
- Midterm exam: 30%
- Final exam: 30%

### Homework

Homework assignments will be made and collected on a regular basis. You may work together on the homework, but what you turn in must represent your understanding of the problems. Late homework will not be accepted unless permission to turn the homework in late is granted in advance.

### Examinations

The midterm exam and final exam will each consist of two portions: an in-class portion covering concepts, and an out-of-class portion covering problem solving. Both portions of the exams will be closed book, closed notes. The midterm exam will cover sections I−IV and the final exam will cover sections V−X. The date for the midterm will be announced at least two weeks in advance. Make-up exams will only be given in documentable emergencies. The midterm and final exam are subject to the VCU Honor System.

### Topics/Schedule

- Introduction and Review of Multiple Linear Regression
- Model
- Assumptions
- Ordinary Least Squares
- Properties of OLS Estimators
- Coefficient of Determination and AdjustedR
^{2} - Predicted Value and Standard Error of Prediction
- Residuals

- Generalized Least Squares and Weighted Regression
- Multicollinearity
- Review of Definition, Centered Model, Impact of Collinearity
- Review of Diagnostics
- Ridge Regression
- Methods of Choosing
*k* - Principal Components Regression

- Influence Diagnostics
- Review of DFFITS, DFBETAS, Cook’s D, COVRATIO
- Sherman-Morrison-Woodbury Theorem
- Multiple Observation Diagnostics
- Singular Value Decomposition and Diagnostic Plots

- Nonlinear Regression
- Gauss-Newton Procedure
- Marquardt Procedure
- Iteratively Reweighted Nonlinear Least Squares (IRWLS)
- Statistical Inference in Nonlinear Regression

- Poisson Regression
- Logistic Regression
- Model
- Data Structures
- Logit Transformation
- Maximum Likelihood Estimation
- Goodness-of-Fit (Lack-of-Fit) Test
- Tests on Subsets of Parameters
- Standard Error of Coefficients
- Measures of Performance

- Generalized Linear Models
- General Concepts
- Exponential Family
- Principles and Restrictions of Generalized Linear Models
- Methods of Testing
- Over Dispersion

- Variance Modeling
- General Concepts
- Dispersion Effects

- Nonparametric Regression, Additional Topics (time allowing)

*Last updated: Spring 2017*

**STAT 791: Special Topics - Time Series Analysis II**

## STAT 791

### Instructor

QiQi Lu, Ph.D.

### References

*Time Series Analysis: with Applications in R, 2nd edition*, by Jonathan D. Cryerand Kung-Sik Chan, 2008, Springer.*Time Series Analysis and its Applications, 2nd edition*, by Robert H. Shumway andDavid S. Stoffer, 2006, Springer.*Time Series: Theory and Methods, 2nd edition*, by Peter J. Brockwell and RichardA. Davis, 1991, Springer.*Introduction to Time Series and Forecasting, 2nd edition*, by Peter J. Brockwelland Richard A. Davis, 2002, Springer.*Multivariate Time Series Analysis*, by Ruey S. Tsay, 2014, Wiley.*Time Series Analysis*, by James D. Hamilton, 1994, Princeton.

### Software

R (a free software environment for statistical computing and graphics)

### Topics

- Introduction to multivariate time series
- State-Space models
- GARCH models
- Transfer Function models

### Assignments

- Assignments will be made as lecture units are completed.
- You must show your work (when possible) in order to receive ANY credit.

### Exams

- Exam dates will be announced one week in advance.
- Each exam is closed-book and closed-notes.
- Formula sheets made up by you are allowed.
- You must show your work (when possible) in order to receive ANY credit.

### Grading

- Assignments: 30%
- Exam 1: 20%
- Exam 2: 20%
- Final project: 30%

Grading scale:A=[90, 100], B=[80, 90), C=[70, 80), D=[60, 70), F=[0, 60)

*Last updated: Spring 2014*

**SSOR 490: Developing Professional Skills in Operations Research and Statistics**

## SSOR 490

### Instructors

Amy Kimbrough, Ph.D., and Jenise Swall, Ph.D.

### Description

This course is part 1 of the senior capstone sequence for studentsmajoring in statistics or operations research. We will focus on career exploration anddevelopment, professional writing, and oral presentation skills. We will also endeavor todiscuss some ethical and professional issues involving the real-world (mis)use of statistics,algorithms, and analytics. Each student will be expected to identify a research questionand begin work on an individual project, which will be completed in the second semester ofthe sequence (SSOR 495).

### Required Text

*The Chicago Guide to Writing about Numbers* (2nd ed.), Jane E. Miller

### Grading Policy

- Participation: 20%
- Career preparation-related assignments: 30%
- Discussion/ Journaling: 20%
- Project: 30%

### Attendance Policy

Attendance and class participation are crucial. We encourage you to participate inclass discussions, to share your ideas orally and in writing, and to provideconstructive feedback to your classmates and the instructors.

*Last updated: Fall 2017*

**OPER/STAT 636: Machine Learning Algorithms**

## OPER/STAT636

### Instructor

Paul Brooks

### Prerequisite(s)

Graduate status in mathematical sciences, systems modeling and analysis,decision sciences and business analytics, computer science, or permission of instructor.

### Required Text

Tan, P.-N., Steinbach, M. and Kumar, V. *Introduction to Data Mining*. Pearson, 2006.

Additional recommended reference:Nocedal, J. and Wright, S.J. *Numerical Optimization*. Springer, 2006.

### Skills Targeted for Improvement

- Analysis of algorithms: Ability to analyze data mining algorithms according to theirbasis in geometry and optimization
- Computer software skills: Ability to manipulate software to derive information fromdata
- Technical writing: Ability to summarize and communicate results of an analysis ofdata
- Technical reading: Ability to evaluate journal articles about data mining algorithms

### Software

The R language and environment for statistical computing

### Grading Policy

Grades will be based on 1 test (25%), 1 project (20%), 5-6 homework assignments (20%), final

exam (20%), 1 paper presentation (10%), and class participation (5%).Assignments that are turned in late will receive a grade of 0%.

### Topics/Schedule

- Introduction to Data Mining andOptimization
- Linear Regression and Unconstrained Optimization
- PCA/SVD and Constrained Optimization

- Classification
- Decision Trees
- Support Vector Machines, Lagrange Multipliers, and Duality
- Empirical Evaluation of Classifiers

- Cluster Analysis
- Minimum Sum-of-Squared Clustering and Nonconvex Optimization
*k*-means, hierarchical clustering, DBSCAN

- Learning Theory
- Bias/Variance Tradeoff
- Consistency and Generalization
- Vapnik-Chervonenkis Theory - Empirical Risk Minimization, Structural Risk Minimization
- Rademacher Theory and Stability
- No Free Lunch Theorem

- Association Analysis

### Attendance Policy

Students who miss class are responsible for learning the material that is coveredin class and for making up all work missed, regardless of the reason for the absence. A grade ofzero will be assigned for tests missed as a result of an unexcused absence. Students must alsoabide by any administrative decisions (e.g., quiz dates) made by the class in their absence.

*Last updated: Fall 2015*

**SSOR 690: Research and Communication Seminar**

## SSOR 690

### Instructor

Spencer Hays

### Prerequisite(s)

While there is no strict prerequisite, students are expected to have the mathematical and statistical maturity to undertake various analyses such as regression, ANOVA, GLM, etc. and verify all their associated assumptions.

### Required Text

There is one textbook required for the course: “Problem Solving: A Statistician’s Guide,” Chatfield, 2nd edition 1995. The extent to which it will be utilized is determined in-class. The text focuses primarily on the communication and consulting components of the course. For technical resources, it is presumed at this point the students are capable in the search and utilization of relevant information and resources. When needed, the professor will provide resources as well.

### Software

This course requires quantitative analysis of data, and presentation of that analysis in both written form and in a presentation format. Therefore the utilization of some type of quantitative software is required, as well as the use of editing and presentation software. Part of the course will include discussion on the benefits and detriments of using various software and languages for analyses, documentation, and presentations.

All statistical packages are acceptable provided the final documents conform to the requirements of the assignments:

- Possible packages include, but are not limited to, R, SPSS, MATLAB, and SAS
- MS Excel output or graphics are discouraged. Reasons for this will be discussed in class
- Learn about R on YouTube

Presentation and documentation materials can be composed using your preferred software. Note that:

- MS Word and PowerPoint are acceptable but can be considerably more time consuming for mathematical notation and graphics.
- LaTeX is capable of publishing both article- and presentation-form documents. There will be a tutorial later in the class on the use of LaTeX.

#### Resources

### Grading Policy

- Data practicums: 50%
- Presentations: 20%
- Peer review: 15%
- In-class exercises/short assignments: 15%

The course grade will be assigned using a scale no harsher than:

- A: ≥ 90
- B: 80 to 89
- F: ≤ 80

(Don’t worry; this will be discussed in class.)

### Data Practicums

There will be 3 to 4 of these comprehensive assignments which are designed to prepare students to work as the lead quantitative analyst on projects in all of industrial, government, health care and academic settings. Students will be given a real life dataset with a description of the problem associated that a researcher or client wishes to be answered. For each data practicum the student will write a/an:

- Preliminary Report - A short and concise document describing the problem that includes summary statistics and a proposed analysis. Minimal statistical inference should be included in this document. This will count 20% towards the total of the data practicum grade.
- Technical Report - A document completely documenting the data analysis associated with the data practicum. This should include a copy of the code used to analyze the data as an appendix. This will count 60% towards the total of the data practicum grade.
- Executive Summary - A one-ish page document that summarizes the problem at hand, the important items from the analysis and the inference which can be made from the data. This will count 20% toward the total for the data practicum grade.

Students will be required to learn and implement statistical methods that may not have been covered in previous courses. In some cases, not all three documents will be required for the practicum; these will be discussed in class.

### Presentations

Each student will give one or more presentations on each of the Data Practicums. The presentations will be between 10 and 30 minutes and provide a complete description of the problem, the methods used and recommendations based on the data. Students will be graded twice for this: once by the instructor and also by other members of the course via peer review.

### Peer Review

Students will peer review other student’s performance on presentations, and all written materials. This is designed to give students a wide variety of feedback on how they are doing. This section will be evaluated on how constructive, useful, and tactful your feedback on each item is. In the case where students are assigned to teems, the peer review component will also include peer evaluations of team members.

### In-Class Exercises, Short Assignments and Guest Speakers

In addition to the other components of the course, occasional in-class exercises such as brief presentations or client simulations will be assigned. Similarly, a short assignment format will be utilized to emphasize important concepts. Reading assignments may also be assigned with comprehension checked in lecture through discussion or exercises. We will also host occasional guest speakers to discuss pertinent topics.

### Attendance Policy

At times while practicums are assigned, class will not be held as means to provide additional time for the project. These instances will be announced well in advance. When class does meet, it is expected that each student will attend due to the interactive nature of the course. There will, of course, be no class on university breaks and holidays, though work may be assigned during these periods.

*Last updated: Fall 2017*