Skip to main content

Table 2 Comparisons of model fit for the PaSS-24

From: Measuring the paradox of self-stigma: psychometric properties of a brief scale

Model

χ2

Df

P value

RMSEA

90% C.I. for RMSEA

CFI

TLI

Robust Chi-Square difference test

Calibration (N = 101)

 (a) One-factor model

963.118

252

< .001

0.167

0.156–0.178

0.728

0.702

 

 (b) Three-factor model

416.229

249

< .001

0.082

0.068–0.095

0.936

0.929

 

 (a) vs (b)

       

Δχ2 = 145.130, Δdf = 3, p < .001

Cross validation (N = 101)

 (a) One-factor model

809.874

252

< .001

0.148

0.137–0.160

0.547

0.504

 

 (b) Three-factor model

379.037

249

< .001

0.072

0.057–0.086

0.894

0.883

 

 (a) vs (b)

       

Δχ2 = 111.816, Δdf = 3, p < .001

Total sample (N = 202)

 (a) One-factor model

1579.617

252

<.001

0.161

0.154–0.169

0.649

0.616

 

 (b) Three-factor model

480.489

249

< .001

0.068

0.059–0.077

0.939

0.932

 

 (a) vs (b)

       

Δχ2 = 238.534, Δdf = 3, p < .001

  1. df degree of freedom, RMSEA Root Mean Square Error of Approximation, C.I. Confidence Interval, CFI Comparative Fit Index, TLI Tucker–Lewis Index