An Exploratory Investigation of Rasch Model Residuals.

Residual patterns should be studied in order to understand when and why data deviate from a model. This paper illustrates some techniques for exploring residual patterns resulting from the difference between observed and expected scores as predicted by a Rasch model for polychotomous data. The score residual divided by its standard deviation is called a standardized residual. A variety of plots of residuals are presented to illustrate residual pattern interpretation. A systematic analysis of residuals can offer the investigator a decision facilitation technique not found in conventional summary fit statistics. (BW)