

Rsqaure vs chisquare in assessment ... 

Message/Author 


I am struggling with deciding between two path models, both of which have a binary outcome variable. The first has an Rsquare of .151, chisquare=163.6, CFI=.479, RMSEA=.032, WRMR=3.082. When I remove one of the predictor variables, I get an Rsquare=.079, chisquare=45.086, CFI=.762, RMSEA=.026, WRMR=2.123. Why would the Rsquare improve, but the fit indicies be worse? Which should be used in deciding the best model? 


Rsquare is not a test of model fit. It says how much variance in a dependent variable is explained by a set of independent variables. A wellfitting model can have low Rsquare values and a poorlyfitting model can have high Rsquare values. 

Back to top 

