Supplemental Material for Enhancing Precision of the Telephone Interview for Cognitive Status–Modified (TICS-M) Using the Rasch Model
Permanent link to Research Commons versionhttps://hdl.handle.net/10289/15811
Rasch analysis begins with examining the overall data fit to the Rasch model as well as individual item fit. It also includes the evaluation of residual correlations across items because it possibly influences fit to the Rasch model. Firstly, the overall model fit requires the estimate of item-trait interaction to be not significant, which is reflected by chi square index (p > .05). Secondly, the fit residuals for individual items should be in the range between −2.50 and +2.50. Thirdly, the residual correlations between individual items should be examined because values above 0.20 indicate local dependency that can affect both individual items and the overall model fit (1). Finally, there should be no DIF due to relevant individual characteristics (i.e. personal factors) meaning that all items should be invariant across different groups (e.g. age, sex). In addition, PSI is used to evaluate reliability in Rasch analysis, which is not the Rasch model fit criteria but reflects how well the scale discriminates between individuals with different levels of the latent trait (e.g. SCC). PSI is interpreted somewhat similar to Cronbach's alpha with values above 0.70 indicating acceptable reliability for group assessments and 0.80 and higher for individual assessments (2).
American Psychological Association
This is an author’s accepted version of an article published in Psychological Assessment. © 2023 APA.