30 Appendix C: Factor Analysis Results #1 The following specific methods were used for the first factor analysis. First, NACE ran checks for normality and found the data reflected a pareto distribution, which is a challenge in CFA. As a result, NACE transformed the data with a log scale and ran the analyses both ways, finding little difference in the results. Below, the results reflect the analyses run with the original pareto distributions. To run the Confirmatory Factor Analyses, NACE ran CFA with lavaan in R with a dataset that contained 2,236 records. For CFA, NACE fixed variance of latent variables to 1, so each item’s loading could be estimated because NACE wanted to examine how all the items specifically load onto the latent variables in this case, so fixing the latent variable variance at 1 was appropriate. NACE ran models with FIML to handle missing data because FIML is regarded as better at producing more stable estimates. NACE ran models with both outliers included and excluded and saw minor differences in their results. NACE decided to keep the outliers because all values were within the acceptable range, were not data input errors, and would likely occur in the field.
RkJQdWJsaXNoZXIy MTM2NjgzMA==