This course extends ordinary least squares regression. Logistic regression allows prediction of categorical dependent variables (e.g. binary variables like use or non-use of social network sites). This course covers the interpretation of coefficients and odds ratios, measures of fit, supporting graphics, and diagnostics and corrective techniques for common problems. Principal components analysis allows a large number of variables to be summarized in a (much) smaller number of factors. This part of the course will cover construction and interpretation of components as well as contrasts to other techniques like item analysis. The goal of this course is to give students a wider range of techniques that they can apply in their own research.

Outcomes: At the end of the course students will be able to: Understand the strengths and limitations of logistic regression; Understand and interpret logistic regression coefficients, odds ratios and significance levels, for both continuous and categorical independent variables; Understand and interpret fit statistics for models; Be able to diagnose and correct the two major problems with logistic regression: outliers and collinearity; Understand different measures of similarity and dissimilarity; Understand and interpret eigenvalues, communalities, factor loadings, and rotations for principal components analysis; Understand the relation between principal components, ordinary regression and logistic regression.

This page was last modified on 25 September 2017