The dynamic structural equation modeling (DSEM) framework incorporates hierarchical latent modeling (HLM), structural equation modeling (SEM), time series analysis (TSA), and time-varying effects modeling (TVEM) to model the dynamic relationship between latent and observed variables. To model the functional relationships between variables, a Gaussian process (GP), by definition of its covariance function(s), allows researchers to define Gaussian distributions over functions of input variables. Therefore, by incorporating GPs to model the presence of significant trend in either latent or observed variables, this dissertation explores the adequacy and performance of GPs in manipulated conditions of sample size using the flexible Bayesian analysis approach. The overall results of these Monte Carlo simulation studies showcase the ability of the multi-output GPs to properly explore the presence of trends. Also, in modeling intensive longitudinal data, GPs can be specified to properly account for trends, without generating significantly biased and imprecise estimates.

Establishing causal relationships is arguably the most important task of the social sciences. While the relationship between the social sciences and the concept of causality has been rocky, the randomized experiment gives us a concrete definition of a causal effect as the difference in outcomes due to the researcher's intervention. However, many interesting questions cannot be easily examined using experiments. Feasibility and ethics limit the use of randomized experiments in some situations and retrospective questions, i.e., working from the observed outcome to uncover the cause, require a different logic. Observational studies in which we observe pairs of variables without any intervention lend themselves to such situations but come with many difficulties. That is, it is not immediately clear whether an observed relationship between two variables is due to a true causal effect, or whether the relationship is due to other common causes. Panel data describe repeated observations of the same units over time. They offer a powerful framework for approaching causal questions with observational data. Panel analysis allows us to essentially use each unit as their own control. In an experiment, random assignment to either treatment and control group makes both groups equal on all characteristics. Similarly, if we compare the same individual pre- and post-treatment, then the two are equal at least on the things that do not change over time, such as sex, date of birth, nationality, etc. Structural equation modeling (SEM) is a group of statistical methods for assessing relationships between variables, often at the latent (unobserved) variable level. The use of SEM for panel analysis allows for a great deal of flexibility. Latent variables can be incorporated to account for measurement error and rule out alternative models. This dissertation focuses on the use of panel data in SEM for causal analysis. It comprises an introduction, four main chapters and a conclusion. After a short introduction (Chapter 1) outlining the goals and scope of the dissertation, Chapter 2 provides an overview of the topic of causality in the social sciences. Since the randomized experiment is often not feasible in social research, special emphasis has been placed on non-experimental, i.e., observational data. The chapter outlines some competing views on causality with non-experimental data, then discusses the two currently dominant frameworks for causal analysis, potential outcomes and directed graphs. It goes on to outline empirical methods and notes their compatibility with SEM. Chapter 3 discusses how panel data can be used to deal with unobserved time-invariant heterogeneity, i.e., stable characteristics that might normally confound analyses. It attempts to show in detail how basic panel regression in SEM works. It also discusses some issues that are not normally addressed outside of SEM, e.g., measurement error in observed variables, effects that change over time, model comparisons, etc. This discussion of the more basic panel regression setup provides a sort of basis for the more complex discussion in the following chapters. Chapter 4 compares and contrasts several ways to model dynamic processes, where the outcome at a particular point in time may affect future outcomes or even the presumed cause later on. It shows that popular recently proposed modeling techniques have much do to with their older counterparts. In fact, the newer modeling techniques do not seem to offer benefit with regards to estimating the causal effects of interest. The chapter focuses on arguably common situations in which the newer techniques may have serious drawbacks. Chapter 5 provides an applied example. It looks to better assess the causal effect of environmental attitudes on environmental behaviour (mobility, consumption, willingness to sacrifice). It touches on many of the aspects from the previous chapters, including the use of latent variables for constructs that are not directly observable, unobserved time-invariant confounders, state dependence (feedback from outcome to outcome), and reverse causality (feedback from outcome to cause). It shows that failure to account for time-invariant confounders leads to biased estimates of the effect of attitudes on behaviour. After controlling for these factors, the effects disappear in terms of mobility and consumption behaviour: when a person's attitudes become more positive, their behaviour does not become more environmentally-friendly. There is, however, a fairly robust effect of attitudes on willingness to sacrifice, even after controlling for unobserved time-invariant confounders, state dependence and reverse causality. This suggests changing attitudes do affect willingness to make sacrifices, holding potential time-invariant confounders, outcome to outcome feedback (essentially habits), as well as some time-varying confounders constant. Finally, Chapter 6 summarizes the previous chapters and provides an outlook for future work.:1. Introduction 2. Causal Inference in the Social Sciences 3. A Closer Look at Random and Fixed Effects Panel Regression in Structural Equation Modeling Using lavaan 4. Equivalent Approaches to Dealing with Unobserved Heterogeneity in Cross-Lagged Panel Models? 5. Re-Examining the Effect of Environmental Attitudes on Behaviour in a Panel Setting 6. Conclusion

No description available.

Low enrollment and high attrition of women in science, technology, engineering, and mathematics (STEM) continues to be an issue for postsecondary institutions. Improvements in representation of women has been seen in some of the agricultural and biological sciences; however, in many of the more math intensive areas such as geosciences, engineering, mathematics/computer science, and physical sciences (GEMP), women continue to be underrepresented leading to underrepresentation in the workforce and further exacerbating gender gaps. Studies suggest the lack of representation is not due to a gap in math ability between men and women, yet underrepresentation remains predominantly within math intensive STEM areas, suggesting something like math self-efficacy (MSE) and math self-concept (MSC) may be impacting enrollment and retention. The research presented here investigates the link between enrollment in GEMP STEM and retention in STEM with the factors of MSE, MSC, and gender. Structural equation modeling (SEM) with Bayesian estimation is used incorporating additional factors from previous research. Study results indicated that MSE and male were both positive and significant indicators of enrollment in GEMP STEM and retention in STEM. MSC was not a significant indicator of retention in STEM but was shown to be significant for GEMP STEM enrollment; however, it was negatively associated with GEMP STEM when combined with MSE. Several program related factors were also shown to be significant indicators of GEMP STEM enrollment and STEM retention. This study highlights the importance of MSE and gender for enrollment and retention and should encourage future efforts towards improving MSE as a possible method of increasing representation of women in underrepresented areas of STEM.

No description available.

Exposure to more types of Adverse Childhood Experiences (ACEs) has been associated with a greater likelihood of general and sexual offending behaviors. However, few studies exist that consider both the impact of varied ACE exposures and community correlates on pathways to offending behaviors in adolescents who have engaged in sexually abusive behaviors. The current study examined these pathways using data collected from archival records of male adolescents (N= 285) who had received treatment for sexually abusive behavior at a youth facility. Structural equation modeling revealed a three-factor model for ACEs, which included: nonsexual abuse and neglect; household dysfunction; and sexual abuse and more passive indicators of sexual boundary problems in the home of origin. Direction and significance of paths between ACEs and the onset, persistence, and nature of maladaptive behaviors differed. Household dysfunction was related to an earlier onset and more persistent nonsexual delinquent offending and contact sexual offending. Conversely, sexual abuse and exposure to sexual boundary problems were associated with an earlier onset of sexually abusive behavior as well as indicators of adolescent-onset, less persistent, and nonviolent delinquency. Nonsexual abuse and neglect were uniquely associated with contact sexual offending. Thus, these findings suggest variations in ACE exposures differentially influence the development, severity, and continuance of nonsexual delinquent and sexually abusive behaviors among these youths. Socioecological variables associated with participants’ counties of origin, including social and economic environment and percentage of rurality, were not retained as covariates due to producing a poor model fit for the data. Additional study with regard to the role of community characteristics on delinquent and sexual offending behaviors is warranted.

The Marriage Checkup (Cordova, Warren & Gee, 2001) was introduced as a brief intervention targeting couples at risk for severe marital distress. The purpose of this study was to examine married couples who participated in The Marriage Checkup for levels of individual and relational stress and severity of presenting problems recorded at intake. Differences were investigated between couples who, though initially requesting the brief Marriage Checkup, elected to continue with traditional marital therapy and couples who only participated in traditional marital therapy. The group means were compared using a structural equation model in order to account for the non-independence of distress within a relationship. Results showed that Marriage Checkup couples reported lower distress levels than couples who received traditional marital therapy even if they transitioned from the Marital Checkup into marital therapy. Additional analyses compared levels of distress and presenting problems for the two Marriage Checkup groups: couples who only completed the Marriage Checkup and couples who also transitioned into traditional marital therapy. Couples who only participated in the Marriage Checkup had lower levels of individual distress for husbands and lower levels of relational distress than did couples who participated in the Marriage Checkup and then transitioned into traditional marital therapy. Clinical implications are discussed.

A child's parents are the primary source of knowledge and learned behaviors for developing children, and the benefits or repercussions of certain parental practices can be long lasting. Although parenting practices affect behavioral outcomes for children, families tend to be diverse in their circumstances and needs. Research attempting to ascertain cause and effect relationships between parental influences and child behavior can be difficult due to the complex nature of family dynamics and the intricacies of real life. Structural equation modeling (SEM) is an appropriate method for this research as it is able to account for the complicated nature of child-parent relationships. Both Frequentist and Bayesian methods are used to estimate the effect of latent parental behavior variables on child aggression and anxiety in order to allow for comparison and contrast between the two statistical paradigms in the context of structural equation modeling. Estimates produced from both methods prove to be comparable, but subtle differences do exist in those coefficients and in the conclusions to which a researcher would arrive. Although model estimates between the two paradigms generally agree, they diverge in the model selection process. The mother's behaviors are estimated to be the most influential on child aggression, while the influence of the father, socio-economic status, parental involvement, and the relationship quality of the couple also prove to be significant in predicting child aggression.

The purpose of this study was (a) to test a hypothesized model of motivation grounded in the Self-Determination Theory within the context of conceptual physical education (CPE), and (b) to explore the strength and directionality of perceived competence for physical activity as a possible mediator for health-related fitness knowledge and actual physical activity behaviors. Participants were 280 high school students who were at the end of a CPE course. Participants completed the Behavioural Regulation in Exercise Questionnaire–2, the Godin Leisure–Time Exercise Questionnaire, the Perceived Competence Scale, and a Health-Related Fitness Knowledge Questionnaire. Structural equation modeling analysis was used to explore the relationships between the variables of health-related fitness knowledge, perceived competence, motivation, and physical activity. The analysis resulted in a modified model that showed a relationship between perceived competence and physical activity, mediated by introjected and identified regulation. Implications and recommendations for physical education professionals are made.

It has been often argued that life events have an impact on our physical and psychological well-being. In general, research supports this connection between life events and general health, though some argue that simply experiencing life events has a measurable and predictable impact our health, while others contend that this effect is mediated by the appraisal process. Further, research has identified a number of different factors (hypothetically stratified into pre-existing beliefs, external resources and demands, and behavioral activation and coping strategies) that may influence appraisal and general health. The current study attempts to integrate these findings by testing structural models of the relationship between life events, life stress, and general health while considering the appraisal process and other potential moderators of appraisal and general health. University students (N=204) were tested using 17 assessment measures representing 7 latent constructs of Life Events, Life Stress, Appraisal, General Health, Beliefs, External, and Activation. Results of the measurement models required model respecification to combine Appraisal and Beliefs into one construct and External and Activation into another construct, resulting in a five-factor hypothetical structural model. The resulting empirical structural model is a partially-mediated model that suggests that appraisal and pre-existing beliefs influence the relationship between life events and life stress, and that life events significantly impact measured life stress. The empirical model also indicates that general health is significantly impacted by life stress, as well as behavioral activation and external resources and demands. Practical implications of the findings and recommendations for further research were discussed.