Rasch Modeling and Differential Item Functioning of the Self-Stigma Scale-Short Version among People with Three Different Psychiatric Disorders

Abstract

Self-stigma is prevalent in individuals with psychiatric disorders and can profoundly affect people. A unified assessment with sound psychometric properties is needed for evaluating self-stigma across psychiatric conditions. The aim of this study was to examine the psychometric properties of the Self-Stigma Scale-Short version (SSS-S) using Rasch modeling. Six-hundred and twelve participants with substance use disorders (n = 319), attention-deficit/hyperactivity disorder (n = 100), and schizophrenia (n = 193) completed the SSS-S. Rasch results confirmed the unidimensionality of the nine items of the SSS-S. The four-point Likert scale of the SSS-S reflected monotonical increases along the self-stigma continuum. No ceiling or floor effects were detected. Among the three subdomains of the SSS-S, cognitive items appeared to be the most robustly endorsed, and behavioral items were the least endorsed. Two items in the SSS-S displayed differential item functioning across the three diagnoses. Additionally, SSS-S scores showed weak to moderate correlation with depression, anxiety, and stress scale scores. The SSS-S had overall satisfactory psychometric properties. Healthcare professionals may use this assessment to assess self-stigma in multiple psychiatric groups, and information gained may facilitate improved care.

Rasch Modeling and Multilevel Confirmatory Factor Analysis for the Usability of the Impact of Event Scale-Revised (IES-R) during the COVID-19 Pandemic

“…The objective of this step is to obtain goodness of fit statistics, which include the p -value of the Chi-Square statistic (non-significant), the Bentler–Bonett normed fit index (NFI) (≥0.90), the Bentler–Bonett non-normed fit index (NNFI) (≥0.90), the comparative fit index (CFI) (≥0.90), Bollen’s incremental fit index (IFI) (≥0.90), the Joreskog–Sorbom goodness of fit index (GFI) (≥0.90), the root mean square residual (RMR) (≤0.08), the standardized root mean square residual (SRMR) (≤0.08), the root mean square error of approximation (RMSEA) (≤0.08), and the 90% confidence interval of RMSEA (90% CI RMSEA) (≤0.08) [ 66 , 68 , 72 , 82 , 83 , 90 , 91 , 93 , 94 , 95 ]. The researcher can check for the re-specified model if the original model is a misfit until the researcher holds the fit model.…”

“…The objective of this step is identifying and meeting the goodness of fit statistics (e.g., NFI (≥0.90), NNFI (≥0.90), CFI (≥0.90), IFI (≥0.90), GFI (≥0.90), RMR (≤0.08), SRMR (≤0.08), RMSEA (≤0.08), and 90% CI RMSEA (LO and UP) (≤0.08)) [ 66 , 67 , 72 , 82 , 91 , 92 , 96 ].…”

“…The Rasch model has the strength of converting ordinal scales (e.g., the five-point Likert scale used in the IES-R) to continuous scales for psychometric testing, regarding if any item in an instrument fits with the underlying construct measured by the instrument. Moreover, the Rasch model identifies whether the ordinal scales follow a monotonic order (i.e., the probabilities of answering a more severe level of PTSD are lower than the probabilities of answering a less severe level of PTSD) [ 66 , 67 , 68 , 69 , 70 , 71 , 72 ]. As such, the Rasch model helps identify potential IES-R items that fit the construct of PTSD.…”

Measurement Invariance and Differential Item Functioning of the Health Literacy Instrument for Adults (HELIA): A Large-Scale Cross-Sectional Study in Iran

“…For the infit and outfit MnSq, values between 0.5 and 1.5 indicate good fit [ 30 ]. For DIF, a DIF contrast less than 1 indicates no substantial DIF [ 31 , 32 ]. For separation reliability, a value > 0.7 indicates acceptability [ 33 ].…”

Comparisons of psychological distress and self-stigma among three types of substance use disorders receiving treatment-as-usual approaches: real-world data from a 9-month longitudinal study

“…Self-stigma is another concern among people with SUDs as these individuals may be viewed as criminals or people with weak personalities, and they may internalize such beliefs. 19 – 21 Because Chinese people value ‘face’, 22 the impression of being a criminal or having a weak personality among people with SUDs may lead them to be stigmatized. When encountering stigmatizing views, people with SUDs may develop self-stigma, which may promote poor psychological adjustment, including poor self-esteem 23 and depression.…”