MIS 84023 Fall 2011 Guiffrida

MIS-84023 Linear Statistical Models

Department of Management and Information Systems

Kent State University

Fall 2011

Instructor       

Dr. Alfred L. Guiffrida

Office:               A-411 Business Administration Building

Office Hours:    Tuesday 3:00 – 6:00; Thursday 3:00 – 6:00 and by appointment

Telephone:        716/954-3504

E-mail:              aguiffri@kent.edu

Course Objectives

Our course is a doctoral seminar on applied linear statistical models. The goal is to expose you to the underlying theory of linear statistical models with heavy emphasis on correlation and regression analysis. The successful application of linear statistical models in your research requires a sound understanding of both the underlying theory and the practical problems encounter in using linear statistical models in practice. Hence, your assignments in this seminar will be an integrated and complementing mixture of theoretical based problems and data driven problems requiring computer analysis.  At the end of the course, students should be able to read published papers found in the literature of your research discipline and be comfortable with how to plan, design, and conduct a statistical analysis using correlation and regression analysis.

Course Textbook

Kunter, M. H., Nachtsheim, C. J., Neter, J. And Li, W. (2005), Applied Linear Statistical Models, 5th Edition, McGraw-Hill/Irwin, ISBN 978-0-07-238688-2

Computer Software

Completion of some assignments in the course will require the use of computer software such as SAS, SPSS or R.

Course Prerequisites and Enrollment Requirements

Doctoral Standing in the KSU School of Business

Enrollment/Withdrawal: Students have responsibility to ensure they are properly enrolled in classes.  You are advised to review your official class schedule (using Student Tools/Flashfast) during the first two weeks of the semester to ensure you are properly enrolled in this class and section.  Should you find an error in your class schedule, you have until September 11, 2011 to correct the error in your class schedule. If registration errors are not corrected by this date and you continue to attend and participate in classes for which you are not officially enrolled, you are advised now that you will not receive a grade at the conclusion of the semester for any class in which you are not properly registered.

For the Fall 2011 semester, the course withdrawal deadline is Sunday, November 6, 2011. Withdrawal before the deadline results in a “W” on the official transcript; after the deadline a grade must be calculated and reported.

Grading Policy

Grades will be based on written assignments. There will be six graded assignments during the term. Each assignment is scored on a 100 point scale. Your overall score (OS) is based on the following formula:

Your letter grade for the course will be assigned based on the following scale.

            OS             Letter Grade           OS          Letter Grade

            93-100             A                     77-79           C+

            90-92               A-                    72-76           C

            87-89               B+                    68-71          C-

            83-86               B                      60-67           D

            80-82               B-                     0-59             F

Academic Integrity

We will follow the University Policy on Academic Integrity.  Academic honesty: Cheating means to misrepresent the source, nature, or other conditions of your academic work (e.g., tests, quizzes, papers, projects, homework assignments) so as to get undeserved credit. The use of intellectual property of others without giving them appropriate credit is a serious academic offence. It is the University’s policy that cheating or plagiarism result in receiving a failing grade (0 points) for the work or course. Repeat offences may result in dismissal from the University.

Students with disabilities

University policy 3342-3-18 requires that students with disabilities be provided reasonable accommodations to ensure their equal access to course content.  If you have a documented disability and require accommodations, please contact the instructor at the beginning of the semester to make arrangements for necessary classroom adjustments.  Please note, you must first verify your eligibility for these through the Student Accessibility Services (contact 330-672-3391 or visit www.kent.edu/sas for more information on registration procedures).

Course Topics (subject to revision)

Note: chapter readings (Ch) are in reference to the Kunter et al. 2005 textbook. Additional materials will be posted to Vista.

I.     Review of probability, expectation and inferential statistical methods (handouts)

II.    Introduction to Correlation Analysis and Simple Linear Regression (Ch 1)

III.   Inferences in Correlation and Regression Analysis (Ch 2)

IV.   Multiple Regression (Ch 6, section 6.1)

V.    Diagnostic and Remedial Measures (Ch 3)

VI.   Matrix Approach to Regression (Ch 5, Ch 6, Ch 7)

VII. Alternative Models to OLS (Handouts)

VIII. Regression Models for Quantitative & Qualitative Predictors (Ch 8)

IX.   Regression Model Selection, Validation and Diagnostics (Ch 9, 10, 11)

X.   Logistic Regression and Generalized Linear Models (Ch 14)

XI.   Nonlinear Regression (Ch 13)