Skip to main content

Table 3 Confirmatory factor analysis of the Addiction Profile Index

From: Application of the Chinese version of the addiction profile index (API) in drug users: an analysis of validity and measurement invariance across genders

Model

χ2

df

p

CFI

TLI

AIC

BIC

RMSEA

SRMR

 

ΔCFI

ΔTLI

Model-Ogel

1523.781

224

<.01

.874

.858

74,446.315

74,823.297

.072

.079

 

–

–

Model-Present

1088.710

224

<.01

.916

.905

73,964.001

74,340.983

.059

.048

 

–

–

Model A

1774.386

448

<.01

.921

.911

123,603.732

124,435.064

.056

.047

 

–

–

Model B

1823.518

467

<.01

.919

.912

123,604.962

124,330.992

.056

.051

B vs. A

−.002

.001

Model C

2012.815

486

<.01

.909

.905

123,769.823

124,390.551

.058

.053

C vs. B

−.01

−.007

Model D

2142.319

509

<.01

.903

.903

123,881.854

124,375.111

.058

.057

D vs. C

−.006

−.002

  1. Notes: Model A, configural invariance; Model B, metric invariance; Model C, scalar invariance; Model D, strict invariance
  2. Abbreviations: df degrees of freedom, TLI Tucker Lewis Index, CFI comparative fit index, RMSEA root mean square error of approximation, SRMR standardized root mean squared residual, BIC Bayesian information criterion, AIC Akaike information criterion
Back to article page

Substance Abuse Treatment, Prevention, and Policy

ISSN: 1747-597X