Indiana University Bloomington

Sociology S650
Categorical Data Analysis

Contact: Scott Long ( 2012-10-07
Offered: Fall, Every Year
Capacity: 30
Sequence: Stat 501/Soc 554: Statistical Methods I: Introduction to Statistics {Note: this title is misleading and should be changed since course is primarily linear regression.}
Pre-Requisites: Stat 501/Soc 554 - linear regression or similar class.
Algebra Required: Notation only
Calculus Required: Concepts
Contact Person for Authorization: Yes by contacting graduate secretary in Statistics or Sociology depending on whether it is being offered as Stat 503 or Soc 650
Instructor: Scott Long
Days Per Week Offered: Two lectures a week; two computer labs
Syllabus: No Syllabus Avaliable
Keywords: regression models; categorical outcomes; logit; probit; maximum likelihood;
Description: Categorical Data Analysis deals with regression models in which the dependent variable is categorical: binary, nominal, ordinal, and count. Models that are discussed include probit and logit for binary outcomes, ordered logit and ordered probit for ordinal outcomes, multinomial logit for nominal outcomes, and Poisson regression and related models for count outcomes.
Books: Lecture notes; Long & Freese. 2005. Regression Models for Categorical Dependent Variables Using Stata, 2nd Edition. Long. 1997. Regression Models for Categorical and Limited Dependent Variables.
Substantive Orientation: Social sciences; non-experimental
Statistical Orientation: non-experimental; maximum likelihood
Applied/Theoretical: applied with explanations (not derivations) of statistical foundations.
Software: Stata
How Software is Used: data analysis, some programming
Problem Sets: Yes, with most involving analysis and interpretation of data.
Data Analysis: Yes as part of problem sets
Presentation: No
Exams: No
Comments: The course is equivalent to Stat 503.