All models were tested using SEM. According to Kline (2005), a good model fit should yield a nonsignificant χ2 value, but this test tends to be too conservative with larger sample sizes. In that case, other fit indices are usually preferred to assess model fit. CFI values at 0.90 or more, root mean square error of approximation (RMSEA) values at 0.10 or less, and standardized root mean square residual (SRMR) values lower than 0.10 indicate adequate model fit. Because of positively skewed distributions, all continuous substance use data were log transformed when they were used in the SEM analyses. The transformation generally improved skewness issues for all substance use variables and kurtosis issues for most variables (see Tables 1, 2 and 3).
