Paper Summary
Share...

Direct link:

Examining Alternative Strategies to Accommodate Categorical Data

Mon, April 16, 12:25 to 1:55pm, Marriott Pinnacle, Floor: Third Level, Dundarave

Abstract

The purpose of our study is to compare the effectiveness of different methods to analyze categorical data. These include robust DWLS procedures (mean- and mean- and variance-adjustments), robust ML with polychoric input and constraints, and the ULS estimator. We will simulate sampling ordinal data from non-normal latent distributions. Data will be analyzed under varying sample sizes, non-normality levels, and number of ordered categories to determine the impact on parameter estimates and model fit

Authors