Skip to main content

Table 1 Item analysis, goodness-of-fit, and reliability assessment of the measurement model (n = 268)

From: Physical and emotional health outcomes after 12 months of public-sector antiretroviral treatment in the Free State Province of South Africa: a longitudinal study using structural equation modelling

Scale

Standardized Loadings1

t Value

Physical QoL

  

   Mobility

0.787***

13.883

   Usual activities

0.936***

34.920

   Pain

0.829***

20.995

   Self-care

0.938***

23.281

Emotional QoL

  

   Satisfaction with life

0.730***

10.561

   Pleasant affect

0.946***

11.394

   Absence of unpleasant affect

0.798***

7.975

Test for Fit

Measurement Model

Criteria for Good Fit

   RMSEA

0.0312

< 0.05

   Normed Fit Index (NFI)

0.985

> 0.9

   Non-Normed Fit Index (NNFI)

0.993

> 0.9

   Comparative Fit Index (CFI)

0.996

> 0.9

Reliability

 

Criteria for Reliability

   Composite reliability (Phys. QoL)

0.892

> 0.7

   Composite reliability (Emo. QoL)

0.829

> 0.7

Validity

 

Criteria for Validity

   χ2 difference test

42.115 (1); P < 0,001

P < 0.05

   Extracted variance test (Phys. QoL)

0.881

> 0.5

   Extracted variance test (Emo. QoL)

0.812

> 0.5

  1. *** P < 0.001
  2. 1The standardized factor loading is the standardized regression coefficient of the latent variable on the indicator (the measured variable). Squaring the factor loading gives us the percentage of variance of the measured variable explained by the latent variable.