P596 | 1436 | Verma

This is the second course in data analysis for graduate students in criminal justice. This course presumes a basic grounding in univariate models and non-parametric statistics including probability theory. We will study methods of analyses for data that involves more than one variable. The primary aim will be interpretation and manipulation of the data, starting with the multivariate normal distribution and proceeding to the multivariate inference theory. Sufficient theory will be developed to facilitate an understanding of the main ideas and examples will be given from criminal justice fields. We will use computers routinely, and familiarity with elementary use of SPSS will be assumed. Topics covered will include matrix algebra, multivariate normal population, inference about means and covariance, multivariate linear models, principal component classification, factor analysis, cluster analysis and if time permits path analysis. Readings: To be announced Requirements: Grades will be based on a combination of quizzes and final examination, plus routine homework. Home Assignments 25% Short Quizzes in Class 20% Mid-Term exam 25% Project Paper 30% The project paper will involve developing a complete paper analyzing some criminal justice data based upon one or more of the techniques learnt in class. Students may take the options of giving a final examination instead of the project. Class Meeting: One 150-minute seminar each week (W, 2:30-5:00P, BH 308) Course Will Satisfy: CJUS Ph.D. research requirement Instructor: Professor Arvind Verma, Criminal Justice Department