Ordinal missing data are common in measurement equivalence/invariance (ME/I) testing studies. However, there is a lack of guidance on the appropriate method to deal with ordinal missing data in ME/I testing. Five methods may be used to deal with ordinal missing data in ME/I testing, including the continuous full information maximum likelihood estimation method (FIML), continuous robust FIML (rFIML), FIML with probit links (pFIML), FIML with logit links (lFIML), and mean and variance adjusted weight least squared estimation method combined with pairwise deletion (WLSMV_PD). The current study evaluates the relative performance of these methods in producing valid chi-square difference tests ( $\Delta {\chi }^2$) and accurate parameter estimates. The result suggests that all methods except for WLSMV_PD can reasonably control the type I error rates of $\Delta {\chi }^2$ tests and maintain sufficient power to detect noninvariance in most conditions. Only pFIML and lFIML yield accurate factor loading estimates and standard errors across all the conditions. Recommendations are provided to researchers based on the results.

The present study assesses the extent of perpetration of physical violence in predominately Hispanic high school students in the Rio Grande Valley, Texas. The relationship between adverse childhood experiences, exposure to interparental violence, attachment, emotion regulation, and impulsivity on two distinct, mutually exclusive, categories of severity of physical teen dating violence (TDV) perpetration is further explored. Participants completed self-report measures as part of a larger, anonymous web-based questionnaire. Two categories (i.e., minor/moderate and severe) were created to discern the contextual variables associated with different levels of severity of physical violence perpetration by males and females. Eight-hundred and twenty-nine 14- to 18-year-old adolescents from four different high schools participated in the study, of whom 407 reported having been in a dating relationship in the last 12 months. The results demonstrate that when only the most severe item of TDV is taken into consideration, the rates of violence perpetration by males and females are almost equal and remarkably lower than those reported in the literature. However, when the assessment includes minor/moderate levels of violence, such as pushing, the rates of violence perpetration by females are twice those of males and are consistent with those reported in the literature. Furthermore, different variables are associated with different levels of severity of violence perpetration. The results support approaches that emphasize the need to take the context of the violence into consideration, since all levels are not equal. The need to take the severity of violence into account in studies assessing dating violence is highlighted.