Measuring autism-associated traits in the general population: Factor structure and measurement invariance across sex and diagnosis status of the Social Communication Questionnaire

Abstract

Using questionnaires in research relies on the expectation that they measure the same things across different groups of individuals. If this is not true, then interpretations of results can be misleading when researchers compare responses across different groups of individuals or use in it a group that differs from that in which the questionnaire was developed. For the questionnaire we investigated, the Social Communication Questionnaire (SCQ), we found that parents of boys and girls responded to questionnaire items in largely the same way but that the SCQ measured traits and behaviors slightly differently depending on whether the children had autism. Based on these results, we concluded that researchers using this questionnaire should carefully consider these differences when deciding how to interpret findings. SCQ scores as a reflection of "autism-associated traits" in samples that are mostly or entirely made up of individuals without an autism diagnosis may be misleading and we encourage a more precise interpretation of scores as a broader indication of social-communicative and behavioral traits.

Keywords: MBRN; MoBa; cohort studies; factor analysis; measurement invariance; psychometrics; statistical; surveys and questionnaires.

Figure 1.

(a) Scree plot and results of the parallel analysis, eignvalues, optimal coordinates, and acceleration factor are present. (b) Fit indices for EFAs extracting 1–10 factors. Fit criteria; RMSEA: excellent < 0.01, good < 0.05, mediocre < 0.08, < 1 poor. CFI and TLI: excellent > 0.97, good > 0.95, acceptable > 0.9, poor < 0.9. SRMR: acceptable < 0.10, good < 0.08.

Figure 2.

Estimated factor loadings from the 5-factor EFA. Darkened bars are items included in the CFA model of the 5-factor model. Dotted gray line shows a 0.4 factor loading.

Figure 3.

Correlations matrices of the 5-factor model when run in subsamples for (a) males (above the diagonal) and females (below the diagonal) and (b) those with a registered diagnosis code of autism in NPR (above) and without (below).

Figure 4.

Differences in standard estimated factor loadings on the five factors shown for both those with a registered diagnosis and those without. Estimates from the configural invariance model.