As shown in Table 1., the hypothesized measurement model (Model 1) is a significantly (P < .001) better fit than any of the alternative models.
The hypothesized measurement model fit the data better than a single factor model: χ 2 (158, N = 572) = 594.29, p = 0.00; RMSEA = 0.088 900 % CI 0.079 to 0.096); CFI = 0.881; and AIC = 738.29) both in terms of the fit statistics and when directly contrasted with a change in AIC.
If a hypothesized measurement model does not show good fit, the model needs to be re-specified and re-tested [ 32].
The aims of this study were to determine the magnitude of the relationship between pain behaviors and a hypothesized measurement model, to compare theoretical models to existing pain scales, and to examine the construct validity of a pain measurement model.
Confirmatory factor analysis, CFA, with AMOS 16 was employed to test the hypothesized measurement model with respect to intention, attitudes, subjective norms and moral norms, specifying the relationship between the observed variables (indicators) and the underlying latent variables (concepts).
All scale reliabilities are approximately 0.6 or above except for the reliability value of 'democracy.' The goodness of fit indicators are useful to assess how well the hypothesized measurement model fits data.
The correlations of the scales with their principal components were as expected and were fairly similar to the hypothesized measurement model of the SF-36v2 in the general population [ 16, 17] and those found for the original SF-36 in previous studies in patients with RA [ 7, 9].
The analysis of the construct validity, i.e. assessing the links between items and relations between items and an underlying dimension, was made by performing confirmatory factor analyses (CFA) to determine the degree of fit between our sample and a hypothesized measurement model [ 24].
In keeping with this process, the end point of the present paper is the detailing of the hypothesized measurement model of the overall burden of back pain from the perspective of individuals with this condition and the description of a proposed program of validation research.
Single-group confirmatory factor analysis was used to evaluate the goodness-of-fit of the hypothesized measurement model for responses to the subscales of the KDCS and SF-36 instruments when analyzed together; and given acceptable goodness-of-fit in each group, multigroup CFA was used to compare the structure of this factor model in the two samples.
