Marshall University Department of Mathematics Student Information Sheet and Syllabus
Marshall University Department of Mathematics Student Information Sheet and Syllabus
DEPARTMENT OF MATHEMATICS
STUDENT INFORMATION SHEET AND SYLLABUS
Course Title/Number MTH 412/512 – Regression Analysis
Section 101
CRN 3269/3286
Semester/Year Fall 2014
Days/Time MW 6:30 ‐ 7:45 PM
Location SH 514 (Smith Hall)
Instructor Dr. Avishek Mallick
Office SH 741A
Phone ext. 3443
E‐Mail [email protected]
Office/Hours MW 5:00‐6:30 PM
TR 3:30‐5:00 PM and by appointment.
University Policies By enrolling in this course, you agree to the University Policies listed below. Please
read the full text of each policy be going to www.marshall.edu/academic‐affairs and
clicking on “Marshall University Policies.” Or, you can access the policies directly by
going to http://www.marshall.edu/academic‐affairs/?page_id=802
Academic Dishonesty/ Excused Absence Policy for Undergraduates/ Computing
Services Acceptable Use/ Inclement Weather/ Dead Week/ Students with Disabilities/
Academic Forgiveness/ Academic Probation and Suspension/ Academic Rights and
Responsibilities of Students/ Affirmative Action/ Sexual Harassment
Course Description and Objectives
This course covers topics in determining regression models; deriving parameter estimates using calculus;
detailed coverage of tests of assumptions and remedial procedures (transformations and weighted least‐
squares); multiple and polynomial regression; tests and corrections for autocorrelation.
The principle objective of the course is to introduce graduate and advanced undergraduate students to the
underlying theory and the practical problems that are encountered in using models in real‐life situation. The
models studied will be linear statistical models for regression. We will also cover the use of the statistical
packages like R and Minitab to fit the models.
Prerequisite
Previous coursework in Probability and Statistics, including knowledge of estimation, confidence intervals, and
hypothesis testing and its use in at least one and two sample problems. Some familiarity with Calculus and
Linear Algebra, or permission of instructor.
The table below shows the following relationships: How each student learning outcomes will be
practiced and assessed in the course.
Course Student Learning Outcomes How students will practice each How student achievement
outcome in this Course of each outcome will be
assessed in this Course
Students will understand how to use In class activities, intensive reading Exams and final project
regression analysis to analyze different of relevant chapters and homework
type of data.
Students will understand the concept of In class activities, intensive reading Exams and final project
regression analysis in the context of of relevant chapters and homework
experimental and sampling designs and
also be able to interpret regression
analysis results in a meaningful context for
application by practitioners in the field.
Students will demonstrate competency in In class activities, intensive reading Final project and
oral and written communication skills. of relevant chapters and homework presentation
Required Text
Title : Applied Linear Statistical Models, 5th edition.
Author : J. Neter et al.
ISBN‐10 : 007310874X
ISBN‐13 : 978‐0‐07‐310874‐2
Publisher : McGraw‐Hill/Irwin
Year : 2004
Additional Requirements: Software/Computing
The R statistical package shall be used for demonstration of some topics in class. It is recommended that R be
used for homework assignments and exams. R is free software that can be downloaded from the web at
http://www.r‐project.org/. It can be installed/compiled on Windows, Mac, and Linux/UNIX machines. You are
encouraged to use the Computer Lab in SH532. In addition the SAS software is installed on those computers for
those of you who would like to use SAS. Students are free to use any other statistical package should they
prefer. However, the instructor will not be able to offer software support for other packages.
Academic Dishonesty: Plagiarism and/or Cheating
Note that plagiarism (the submission as one’s own work of any oral, graphic, or written material wholly or in
part created by another), is a form of academic dishonesty. Sanctions for academic dishonesty shall be imposed
in accordance with university’s guidelines on such matter. Also note that in a case where a student is suspected
to have cheated, the student may be asked to re‐take the test. And where the student is found or confirmed to
have cheated, a zero grade will be awarded to the student.
You may wish to refer to other university policies concerning academic dishonesty at,
http://www.marshall.edu/wpmu/academic‐affairs/policies/#AcademicDishonesty
Attendance Policy
Students are expected to attend all scheduled classes. It is the student’s responsibility to find out what was
discussed in a missed class. Although, attendance records will not be used to compute grades (except possibly in
borderline cases), however, missing class can be expected to significantly reduce your chances of success. Note
also that it is the student’s responsibility to present approved notice of any absence that would be excused
under the terms and regulations stipulated by the university.
Student behavior
Students are advised to turn their cell phones and other noise generating devices off prior to entering the class.
In the case where a student awaits any emergency call, the noise should be restricted and made personal. And in
this case, I should be notified as soon as the student enters the class. Food items, apart from water or soft drink,
are not allowed in the class. The reading of newspapers and other unrelated materials while the class is in
session is prohibited. Please ensure that other students are respected.
Grading Policy and Exam dates
The final grade will be based on the following components:
Homework Assignments worth 25 points each (30% of the final grade).
Midterm Exam worth 100 points (20% of the final grade). The exam will be held on Thursday, October
15. It will cover all of the materials presented in class corresponding to Chapters 1 through 5 of the
book. You will be expected to know both the practical applications and the theory.
Final Project worth 100 points (25% of the final grade). The project will be due on the last day of the
class.
Final Exam worth 100 points (25% of the final grade). It will cover all of the materials presented in class
corresponding to Chapters 6 through 11 of the book.
The semester grade will be based on the percentage of the total possible points, using the following scale.
90 ‐100% ‐‐ A
80 ‐ 89% ‐‐ B
70 ‐ 79% ‐‐ C
60 ‐ 69% ‐‐ D
00 ‐ 59% ‐‐ F
FINAL EXAMINATION: Monday December 08 [6:00 PM – 8:00 PM]
Course coverage
1. An introduction to regression. Motivating examples, an overview of the objectives of regression analysis.
2. Simple Linear Regression. (Most of Chapters 1 ‐ 4: Explicit readings assigned as we move through the
material)
The regression model (1.1‐1.5)
Estimation of the regression coefficients and error variance (1.6‐1.8).
Inferences for the regression coefficients. (2.1‐2.3, 4.1)
Estimating the expected response at a particular x; one‐at‐a‐time and simultaneous confidence
intervals.(2.4, 2.6, 4.2)
Predicting future observations. (2.5,4.3)
The Analysis of Variance approach to regression and general linear tests (2.7, 2.8)
Assessing model assumptions and a first look at remedial measures. (Parts of Chapter 3)
3. An introduction to multiple linear regression models (section 6.1, description of models in 8.1 and 8.2)
4. Regression models in matrix form.(Section 5.1‐5.4, the definition of an inverse in 5.6, 5.8‐5.9, 6.2)
5. Multiple Linear Regression (5.10‐5.13, much of Chapters 6, 7 and 8)
Estimation of the regression coefficients and error variance.
Inferences for the regression coefficients.
Estimating the expected response at a particular x; one‐at‐a‐time and simultaneous confidence
intervals.
Predicting future observations.
The Analysis of Variance approach to regression and general linear F‐tests
6. More on diagnostics and tests for assessing model assumptions with some on measures to
accommodate violations of usual assumptions. (Parts of Chapters 10 and 11)
7. Model building/variable selection (Ch. 8)
8. An introduction to nonlinear regression models. (Some of 13 and 14) (if time permits)