Time-to-event analysis or equivalently, survival analysis deals with two variables simultaneously: when (time information) an event occurs and whether an event occurrence is observed or not during the observation period (censoring information). In behavioral and social sciences, the event of interest usually does not lead to a terminal state such as death. Other outcomes after the event can be collected and thus, the survival variable can be considered as a predictor as well as an outcome in a study. One example of a case where the survival variable serves as a predictor as well as an outcome is a survival-mediator model. In a single survival-mediator model an independent variable, X predicts a survival variable, M which in turn, predicts a continuous outcome, Y. The survival-mediator model consists of two regression equations: X predicting M (M-regression), and M and X simultaneously predicting Y (Y-regression). To estimate the regression coefficients of the survival-mediator model, Cox regression is used for the M-regression. Ordinary least squares regression is used for the Y-regression using complete case analysis assuming censored data in M are missing completely at random so that the Y-regression is unbiased. In this dissertation research, different measures for the indirect effect were proposed and a simulation study was conducted to compare performance of different indirect effect test methods. Bias-corrected bootstrapping produced high Type I error rates as well as low parameter coverage rates in some conditions. In contrast, the Sobel test produced low Type I error rates as well as high parameter coverage rates in some conditions. The bootstrap of the natural indirect effect produced low Type I error and low statistical power when the censoring proportion was non-zero. Percentile bootstrapping, distribution of the product and the joint-significance test showed best performance. Statistical analysis of the survival-mediator model is discussed. Two indirect effect measures, the ab-product and the natural indirect effect are compared and discussed. Limitations and future directions of the simulation study are discussed. Last, interpretation of the survival-mediator model for a made-up empirical data set is provided to clarify the meaning of the quantities in the survival-mediator model.

Parental over-control (excessively restrictive and regulatory parenting behaviors) has been consistently identified as a robust risk factor in the development and maintenance of child anxiety problems. However, current understanding of the parental over-control to child anxiety relation is limited by a lack of specificity. The broad ‘parental over-control’ construct represents a heterogeneous category of related but distinct parenting behaviors each of which may exert a unique effect on child anxious emotion. Still, research to date has generally failed to consider this possibility. Moreover, culturally cognizant theory and emerging empirical evidence suggest cross-ethnic (Caucasian vs. Hispanic/Latino) differences in the utilization of various parenting strategies as well as the effects of parenting behaviors on child outcomes. But, only a handful of studies have considered the potential differences in the functioning of parental over-control behaviors within a Hispanic/Latino cultural framework. Using a sample of 98 pre-adolescent children at-risk for anxiety problems, the present study sought to further explicate the association between parental over-control and child anxiety symptoms in the context of ethnic and cultural diversity. Results suggest that parents’ use of overprotection and (lack of) autonomy granting might be particularly relevant to child anxiety, compared to parental intrusiveness and behavioral control. Findings also indicate that some youth may be more vulnerable to parental over-control and suggest that cultural values may play a role in the relation between over-controlling parenting and child anxiety symptoms. Knowledge about cross-cultural variations in the relation among parental over-control behaviors and the development of anxiety symptoms is important because it can improve the cultural robustness of child anxiety theory and has potential to inform culturally sensitive child anxiety prevention and intervention efforts.

Although substantial research has examined individual, family, and peer factors that contribute to predicting adolescent alcohol use, limited attention has been devoted to the unique role of romantic partners and little consideration has been given to the potential importance of romantic relationship seriousness. Data from Waves I and II of the National Longitudinal Study of Adolescent Health (Add Health) were used to assess the relation between romantic relationship seriousness and binge drinking and drinking consequences one year later among 14-18 year-olds (n= 928 adolescents; 54.1% female). Main effects of relationship seriousness and moderating effects of adolescent age, partner age, adolescent age by partner age, parental alcoholism, and gender were examined separately for each drinking outcome using zero-inflated Poisson regression (ZIP) models. Relationship seriousness and study covariate interactions were also examined. ZIP models estimate (a) a logistic regression that distinguishes between individuals whose values can only be zero on the outcome (i.e., a structural zero class) and individuals with count values ranging from zero to any other positive integer (i.e., a non-structural zero class), and (b) a Poisson regression predicting count values among the non-structural zero class. Results showed trends towards significance for relations between relationship seriousness and binge drinking and drinking consequences among non-structural zero classes. As hypothesized, increased relationship seriousness predicted less frequent binge drinking and fewer drinking consequences. The relation between relationship seriousness and binge drinking was moderated by peer alcohol use; the negative relation between relationship seriousness and binge drinking frequency was significant among adolescents who reported 0-2, but not 3, close friends who drink. The relation between relationship seriousness and number of drinking consequences was moderated by gender, adolescent delinquency (covariate), peer alcohol use (covariate), and Wave I drinking consequences (control variable). Specifically, a significant relation between relationship seriousness and number of drinking consequences was revealed only for females and only for adolescents who reported high consequences at Wave I, and was significant among adolescents who reported 0-2 close friends who drink and low delinquency. Results indicate that relationship seriousness can protect adolescents in terms of drinking outcomes, which could have implications for prevention efforts.

Researchers who conduct longitudinal studies are inherently interested in studying individual and population changes over time (e.g., mathematics achievement, subjective well-being). To answer such research questions, models of change (e.g., growth models) make the assumption of longitudinal measurement invariance. In many applied situations, key constructs are measured by a collection of ordered-categorical indicators (e.g., Likert scale items). To evaluate longitudinal measurement invariance with ordered-categorical indicators, a set of hierarchical models can be sequentially tested and compared. If the statistical tests of measurement invariance fail to be supported for one of the models, it is useful to have a method with which to gauge the practical significance of the differences in measurement model parameters over time. Drawing on studies of latent growth models and second-order latent growth models with continuous indicators (e.g., Kim & Willson, 2014a; 2014b; Leite, 2007; Wirth, 2008), this study examined the performance of a potential sensitivity analysis to gauge the practical significance of violations of longitudinal measurement invariance for ordered-categorical indicators using second-order latent growth models. The change in the estimate of the second-order growth parameters following the addition of an incorrect level of measurement invariance constraints at the first-order level was used as an effect size for measurement non-invariance. This study investigated how sensitive the proposed sensitivity analysis was to different locations of non-invariance (i.e., non-invariance in the factor loadings, the thresholds, and the unique factor variances) given a sufficient sample size. This study also examined whether the sensitivity of the proposed sensitivity analysis depended on a number of other factors including the magnitude of non-invariance, the number of non-invariant indicators, the number of non-invariant occasions, and the number of response categories in the indicators.

The present study applied latent class analysis to a family-centered prevention

trial in early childhood to identify subgroups of families with differential responsiveness to the Family Check-up (FCU) intervention. The sample included 731 families of 2-year- olds randomized to the FCU or control and followed through age five with yearly follow up assessments (Dishion et al., 2014; Shaw et al., 2015). A two-step mixture model was used to examine whether specific constellations of family characteristics at age 2 (baseline) were related to intervention response at age 3, 4, and 5. The first step empirically identified latent classes of families based on a variety of demographic and adjustment variables selected on the basis of previous research on predictors of response to the FCU and parent training in general, as well as on the clinical observations of FCU implementers. The second step modeled the effect of the FCU on longitudinal change in children's problem behavior in each of the empirically derived latent classes. Results suggested a five-class solution, where a significant intervention effect of moderate-to- large size was observed in one of the five classes. The families within the responsive class were characterized by child neglect, legal problems, and mental health issues. Pairwise comparisons revealed that the intervention effect was significantly greater in this class of families than in two other classes that were generally less at risk for the development of disruptive behavior problems, and post hoc analyses partially supported these results. Thus, results indicated that the FCU was most successful in reducing child problem behavior in the highly distressed group of families. We conclude by discussing the potential practical utility of these results and emphasizing the need for future research to evaluate this approach's predictive accuracy.

Asian American (AA) adolescents and young adults are at risk for poor psychological adjustment and diminished health. Parental involvement and intergenerational gap in acculturation (IGA) have been independently associated with intergenerational acculturative conflict, a common stressor in the AA population. However, few studies have tested how the influence of parental involvement on intergenerational acculturative conflict/family cohesion and subsequent psychological adjustment may vary depending on IGA; and even fewer studies have investigated how such models apply to AA general health. The goals of the present study were, therefore, to identify pathways linking these acculturative family processes to AA young adult general health in a large sample of Filipino and Southeast Asian (SEA) families. Analyses utilized data from the Children of Immigrants Longitudinal Study (CILS; Portes & Rumbaut, 2001), a national longitudinal study of children from immigrant families. Results suggested that although Filipino and SEA families may differ in the acculturative processes that contribute to intergenerational acculturative conflict and family cohesion, depressive symptoms are an important mechanism through which these family outcomes in adolescence influence young adult general health outcomes in both Filipino and SEA families. This investigation serves to inform future programs aimed at providing targeted interventions for AAs at risk for long-term psychological disorders and physical health problems.

Internalizing symptoms are prevalent among adolescents, especially among Latinos, and can have negative consequences on health and development. Understanding the risk and protective factors leading to internalizing difficulties among Latino youth is critical. The current study sought to assess the effects of family risk and peer social rejection in the seventh grade on internalizing symptoms in the tenth grade, and the potential buffering effects of social support from family and from friends, among a sample of 749 Mexican American youth. Structural equation modeling was used to examine pathways from seventh grade family risk and peer social rejection to internalizing symptoms in the tenth grade. Perceived social support from family and perceived social support from friends were tested as moderators of these relations. Gender differences in these pathways were also assessed. Results showed that family risk did not predict tenth grade internalizing symptoms, but that peer social rejection predicted increased internalizing symptoms for girls. Furthermore, buffering effects were not confirmed; rather social support from both friends and family had no effect on the relation between family risk and internalizing symptoms, and high levels of social support from both sources amplified the effect of peer social rejection on internalizing symptoms. Secondary analyses suggested that at low levels of social support from both sources, peer social rejection predicted decreased internalizing symptoms for males. Limitations and implications for prevention and future research are discussed.

This dissertation examines a planned missing data design in the context of mediational analysis. The study considered a scenario in which the high cost of an expensive mediator limited sample size, but in which less expensive mediators could be gathered on a larger sample size. Simulated multivariate normal data were generated from a latent variable mediation model with three observed indicator variables, M1, M2, and M3. Planned missingness was implemented on M1 under the missing completely at random mechanism. Five analysis methods were employed: latent variable mediation model with all three mediators as indicators of a latent construct (Method 1), auxiliary variable model with M1 as the mediator and M2 and M3 as auxiliary variables (Method 2), auxiliary variable model with M1 as the mediator and M2 as a single auxiliary variable (Method 3), maximum likelihood estimation including all available data but incorporating only mediator M1 (Method 4), and listwise deletion (Method 5).

The main outcome of interest was empirical power to detect the mediated effect. The main effects of mediation effect size, sample size, and missing data rate performed as expected with power increasing for increasing mediation effect sizes, increasing sample sizes, and decreasing missing data rates. Consistent with expectations, power was the greatest for analysis methods that included all three mediators, and power decreased with analysis methods that included less information. Across all design cells relative to the complete data condition, Method 1 with 20% missingness on M1 produced only 2.06% loss in power for the mediated effect; with 50% missingness, 6.02% loss; and 80% missingess, only 11.86% loss. Method 2 exhibited 20.72% power loss at 80% missingness, even though the total amount of data utilized was the same as Method 1. Methods 3 – 5 exhibited greater power loss. Compared to an average power loss of 11.55% across all levels of missingness for Method 1, average power losses for Methods 3, 4, and 5 were 23.87%, 29.35%, and 32.40%, respectively. In conclusion, planned missingness in a multiple mediator design may permit higher quality characterization of the mediator construct at feasible cost.

Longitudinal data from European-American (EA) and Mexican-American (MA) families (n = 179 mothers, fathers, and youth; 41% MA) was used to test a bio-psycho-cultural model of the effect of non-responsive parenting on externalizing problems in young adult offspring through the effect on the stress response system. Parenting behavior (acceptance, rejection, harsh discipline) was assessed when children were in late childhood (12-13 years), cortisol samples were collected during late adolescence (18-19 years), and externalizing problems were measured in young adulthood (21-22 years). Latent profile analyses were used to examine patterns of parenting behavior in EA and MA families. A path analysis framework was used to examine how non-responsive parenting interacted with acceptance to predict adolescent stress response and subsequent externalizing problems in EA and MA young adults. Results showed different patterns of parenting behavior in EA versus MA families, with MA families demonstrating a profile of high acceptance and high non-responsiveness at higher rates than EA families. In MA families, youth adherence to the traditional cultural value of familismo related to more positive perceptions of parenting behavior. Across ethnic groups, parent rejection only predicted higher externalizing problems in young adults when acceptance was high. The effect of parent harsh discipline on offspring stress response differed by ethnicity. In MA families, harsh discipline predicted dysregulated stress response in youth when acceptance was low. In EA families, harsh discipline did not relate to youth stress response. Overall, results increase the understanding of normative and adaptive parenting behaviors in MA families. Findings inform the development of culturally-competent parenting-focused interventions that can better prevent dysregulated stress response and externalizing behavior problems in ethnically diverse youth.