If the full sequence of invariance tests was verified, then total measurement invariance across studies was deemed to be present.
Table 2 shows fit indices for strict and partial invariance models and Table 3 shows results of invariance tests of specific parameters.
Results are discussed in light of country characteristics, challenges of measurement invariance testing, and potential future research using PIAAC data.
Thus, they represent the starting point of measurement invariance testing.
Table 3 displays the results of the invariance testing for the intercorrelated three-factor model.
Because the large number of anticipated invariance tests (i.e., 40-50) will produce a more stringent adjusted p-value, we expected that using Bonferroni-adjusted p values would reduce the bias toward rejecting invariance hypotheses via the likelihood-ratio test.
Invariance testing was conducted by imposing a series of hierarchical equality constraints across these two samples.
Invariance testing proceeded by comparing the chi-square value of this model to a model where item thresholds were constrained to equality across studies (scalar invariance).
Consequently, further measurement invariance testing was skipped (Meredith, 1993). 2 However, test of measurement invariance among older adults for FACE versus SELF conditions reached close fit for the configural invariance model (chi-sqare/ df = 462/80, CFI =.972, TLI =.927, RMSEA =.042) and for the weak invariance model (chi-sqare/ df = 545/130, CFI =.970, TLI =.951, RMSEA =.034).
For our case, three levels of invariance were tested: configural invariance, measurement invariance, and structural invariance (Byrne 2010).
