UNLV Department of Mathematical Sciences

STA 761: Regression Analysis I

Teaching & Class Materials

Welcome to the course homepage for STA761. If you are a student in this class you should check this site frequently for updated information and announcement. 

graduate Program: (MS, PhD)

Related Course:  [STA762]   [STA715]

I. Outline of the Course

 

Instructor: Hokwon A. Cho, Ph.D., Associate Professor, Office: CDC 1008 (Building #10, Room 1008), Office phone: 895-0393 (Math. Sci. dept. office: 895-3567), E-mail: cho@unlv.nevada.edu.

Class Time and Location: Tu, Th 8:30AM - 9:45AM, CBC C-322.

Office Hours: Tu & Th: 1:30PM-3:30PM or by appointment.

Textbook: Introduction to Regression Analysis , Revised & updated Ed. (2010), by M. Golberg and H. Cho, Wessex Institute of Technology, Southampton, UK.

 

Description of the Course: This course provides both foundation and applied perspectives of regression analysis, as a gateway to understanding statistical modeling. The emphasis will be placed on the theoretical foundation, statistical rationale, the investigation of the relationship among variables in a data set, and further advanced topics, models and recent developments. Among topics to be covered will be

 

                1.         Basic concepts and background - Probability space, random variables (or vectors), normal distribution and related distributions, estimation, testing hypothesis, (matrix algebra).

                2.         Simple linear regression - Regression overview, least-squares method, Gauss-Markov theorem, ANOVA approach, lack of fit test, assessing model validity, transformation.

                3.         Multiple regression analysis - Matrix approach, multiple linear regression models, quality fit and prediction, HAT matrix, extra sum of squares principles.

                4.         Residual analysis, diagnostics and remedies - Analysis of residuals, plotting residuals, PRESS statistics, transformation, correlated errors.

                5.         Further models in regression - Polynomial models, indicator variables, modeling categorical variables, logistic regression, generalized linear model, selecting models, multicollinearity, ridge regression, other alternatives.

                6.         Selecting and criteria of regressions - Model misspecification, predictive criteria, methods of selecting models.

 

Homework: All homework assignments will be given in class and expected to turn in on time. No late homework will be accepted. Some of the problems will be discussed in class.

 

Exams: Two midterm tests will be most likely on 5th/6th and 10th/11th week and a final exam will be given according to the university calendars and schedules.

 

Grading:    The course grade is based upon the following: (1) homework assignments 20% (2) two mid-semester exams 25% each, and (3) a final exam 30%.  Grade Scale: A-A: 85% or above, B-B: 75% or above, C-C: 65% or above, D-D: 55% or above, F: Below 55%.

 

University Academic Policies on the Academic Misconduct, Copyright, Disability Resources Center (DRC), Tutoring, Writing Center, and Religious Holidays: click the next è University Academic Policies.

 

II. Textbook Information

 

Title:  Introduction to Regression Analysis, 452 pp + xiv. Revised & updated Edition (2010).

Publisher:  Wessex Institute of Technology, WIT Press, Southampton, United Kingdom.

Authors:  Michael Golberg and Hokwon Cho

ISBN-13:  978-1-85312-624-6        ISBN-10:  1-85312-624-6

 

The book was basically written for the introductory graduate level and for researchers.  The mathematical level is medium and analytical. Anyone who studied and understand the undergraduate senior level of linear algebra and mathematical statistics will have no major difficulties to read the book.  è & Textbook website &

 

Errata:

§  For the First Edition (2004), printed in 2004 and 2007: [Errata P2]

§  For the Revised and Updated Edition (2010): [Errata P3]

 

III. Bulletin Board

 

List of References and Further Readings for the course: click next è [List of Reference & Readings]

To see the lecture and homework schedule: click next  è [Lecture & HW schedule]

 

Announcements:

1.       Welcome to STA 761.

 

IV. Handouts, Data Sets & Other Resources

 

Handouts & Statistical Tables:

§  [Table for Discrete and Continuous Probability Distributions]

§  [Table for Confidence Intervals & Testing Hypotheses]

 

Data Sets:

Copier data

Hunting Trip data

Bank data

Body Fat data

Snow data

Track data

Mole Fraction data

 

 

 

 

 

 

 

 

o    Statistical Software & Language:  | R | S-Plus | Minitab | SAS/JMP | SPSS | STATA | BMDP |

o    Search Journal Articles:           |JSTOR | MathSciNet | Ingenta | CIS  | Thomson | Wikipedia |

 

Ø  Journals:   | Statistics | Probability | Related Journals | Mathematics |

Ø  Societies:   | IMS | ASA | IMS BulletinSIAM | AMS | MAA |                    è More Link?

 

· Home   · Research   · Teaching & Class  · Link  · Math  · UNLV

 

© 2006-2018  Hokwon Cho