Multicollinearity: What Is It and What Can We Do About It? - Deanna Naomi Schreiber-Gregory, Henry M. Jackson Foundation

Multicollinearity can be briefly described as the phenomenon in which two or more identified predictor variables in a multiple regression model are highly correlated. The presence of this phenomenon can have a negative impact on the analysis as a whole and can severely limit the conclusions of the research study. This paper reviews and provides examples of the different ways in which multicollinearity can affect a research project, and tells how to detect multicollinearity and how to reduce it once it is found. In order to demonstrate the effects of multicollinearity and how to combat it, this paper explores the proposed techniques by using the Youth Risk Behavior Surveillance System data set. This paper is intended for any level of SAS® user. This paper is also written to an audience with a background in behavioral science or statistics.

Click here to download the companion paper.

An Introduction to Latent Structure Analyses - Deanna Naomi Schreiber-Gregory, Henry M. Jackson Foundation

This paper looks at several ways to investigate latent variables in survey analyses and how to utilize them in regression models. An introduction to the concept and theory behind latent structure analysis will be reviewed and an overview of available LSA procedures will be explored. The five different SAS® procedures latent analysis procedures explored in this paper are PROC LCA, PROC LTA, PROC TRAJ, PROC FACTOR and PROC CALIS. A case study will then be performed utilizing the latent variables identified from within these procedures and applied to a regression model. The effect of the latent variables on the fit and use of the regression model compared to a similar model using observed data will then be reviewed. The model explored in this study looks at adolescent risk behaviors and their effect on suicidal ideation.  Data was analyzed using SAS 9.4. This paper is intended for moderate to advanced level SAS® users. This paper is also written to an audience with a background in behavioral science and/or statistics.

About the Author

Deanna is a Data Analyst and Research Associate through the Henry M Jackson Foundation. She is currently contracted to USUHS and Walter Reed National Military Medical Center in Bethesda, MD. Deanna has an MS in Health and Life Science Analytics, a BS in Statistics, and a BS in Psychology, and has presented as a contributed and invited speaker at over 40 local, regional, national, and global SAS user group conferences since 2011.