Matching Items (4)
Filtering by
- All Subjects: adolescents
- Creators: Tein, Jenn-Yun
Description
Random Forests is a statistical learning method which has been proposed for propensity score estimation models that involve complex interactions, nonlinear relationships, or both of the covariates. In this dissertation I conducted a simulation study to examine the effects of three Random Forests model specifications in propensity score analysis. The results suggested that, depending on the nature of data, optimal specification of (1) decision rules to select the covariate and its split value in a Classification Tree, (2) the number of covariates randomly sampled for selection, and (3) methods of estimating Random Forests propensity scores could potentially produce an unbiased average treatment effect estimate after propensity scores weighting by the odds adjustment. Compared to the logistic regression estimation model using the true propensity score model, Random Forests had an additional advantage in producing unbiased estimated standard error and correct statistical inference of the average treatment effect. The relationship between the balance on the covariates' means and the bias of average treatment effect estimate was examined both within and between conditions of the simulation. Within conditions, across repeated samples there was no noticeable correlation between the covariates' mean differences and the magnitude of bias of average treatment effect estimate for the covariates that were imbalanced before adjustment. Between conditions, small mean differences of covariates after propensity score adjustment were not sensitive enough to identify the optimal Random Forests model specification for propensity score analysis.
ContributorsCham, Hei Ning (Author) / Tein, Jenn-Yun (Thesis advisor) / Enders, Stephen G (Thesis advisor) / Enders, Craig K. (Committee member) / Mackinnon, David P (Committee member) / Arizona State University (Publisher)
Created2013
Description
Parenting approaches that are firm yet warm (i.e., authoritative parenting) have been found to be robustly beneficial for mainstream White Americans youths, but do not demonstrate similarly consistent effects among Chinese Americans (CA) adolescents. Evidence suggests that CA adolescents interpret and experience parenting differently than their mainstream counterparts given differences in parenting values and child-rearing norms between traditional Chinese and mainstream American cultures. The current study tests the theory that prospective effects of parenting on psychological and academic functioning depends on adolescents' cultural frameworks for interpreting and understanding parenting. CA adolescents with values and expectations of parenting that are more consistent with mainstream American parenting norms were predicted to experience parenting similar to their White American counterparts (i.e., benefiting from a combination of parental strictness and warmth). In contrast, CA adolescents with parenting values and expectations more consistent with traditional Chinese parenting norms were predicted to experience parenting and its effects on academic and psychological outcomes differently than patterns documented in the mainstream literature. This study was conducted with a sample of Chinese American 9th graders (N = 500) from the Multicultural Family Adolescent Study. Latent Class Analysis (LCA), a person-centered approach to modeling CA adolescents' cultural frameworks for interpreting parenting, was employed using a combination of demographic variables (e.g., nativity, language use at home, mother's length of stay in the U.S.) and measures of parenting values and expectations (e.g., parental respect, ideal strictness & laxness). The study then examined whether prospective effects of parenting behaviors (strict control, warmth, and their interaction effect) on adolescent adjustment (internalizing and externalizing symptoms, substance use, and GPA) were moderated by latent class membership. The optimal LCA solution identified five distinct cultural frameworks for understanding parenting. Findings generally supported the idea that effects of parenting on CA adolescent adjustment depend on adolescents' cultural framework for parenting. The classic authoritative parenting effect (high strictness and warmth leads to positive outcomes) was found for the two most acculturated groups of adolescents. However, only one of these groups overtly endorsed mainstream American parenting values.
ContributorsLiu, Freda Fangfang (Author) / Gonzales, Nancy A. (Thesis advisor) / Tein, Jenn-Yun (Committee member) / Yoo, Hyung Chol (Committee member) / Barrera, Manuel (Committee member) / Arizona State University (Publisher)
Created2011
Description
This study aimed to utilize multiple informant reports to examine whether effortful control (EC) varies across the home and school context among ethnically diverse adolescents attending middle schools in low-income communities and how patterns of variation across context are differentiated by measures of academic functioning and risky behavior. 763 adolescents (50.2% male; Mage = 12 years), their primary caregivers, and two teachers completed measures of adolescents’ EC. Adolescents reported on aspects of academic functioning and risky behavior. Archival data on grade point average (GPA) were collected from schools and adolescents completed the Go/No-Go computer task. Latent profile analysis revealed three reporting patterns: Equal at Home and School (EHS; 43%), Higher at Home and Lower at School (HHLS; 35%), and Lower at Home and Higher at School (LHHS; 22%). Relative to EHS adolescents, HHLS adolescents were less likely to have greater levels of self-reported EC and LHHS adolescents were more likely to have greater self-reported levels of EC. Regarding academic functioning, compared to the EHS adolescents, HHLS adolescents were less likely to have a higher and LHHS adolescents were more likely to have a higher accuracy rate on the Go/No-Go task and have a higher GPA. Compared to HHLS adolescents, LHHS adolescents were more likely to have a higher accuracy rate and a higher GPA. Further, compared to EHS adolescents, HHLS adolescents were more likely to have higher levels of externalizing behavior and the LHHS adolescents were less likely to have higher levels of externalizing behavior. Compared to HHLS adolescents, LHHS adolescents were less likely to have higher levels of externalizing behavior. This study highlights the importance of considering context in the study of EC and the potential use of multiple informants to identify meaningful variation across contexts. In addition, findings from this study can help inform decision-making in prevention and intervention efforts in support of academic outcomes for marginalized youth.
ContributorsPerez, Vanesa Marie (Author) / Gonzales, Nancy (Thesis advisor) / Tein, Jenn-Yun (Committee member) / Lemery-Chalfant, Kathryn (Committee member) / De Los Reyes, Andres (Committee member) / Arizona State University (Publisher)
Created2023
Description
The Partition of Variance (POV) method is a simplistic way to identify large sources of variation in manufacturing systems. This method identifies the variance by estimating the variance of the means (between variance) and the means of the variance (within variance). The project shows that the method correctly identifies the variance source when compared to the ANOVA method. Although the variance estimators deteriorate when varying degrees of non-normality is introduced through simulation; however, the POV method is shown to be a more stable measure of variance in the aggregate. The POV method also provides non-negative, stable estimates for interaction when compared to the ANOVA method. The POV method is shown to be more stable, particularly in low sample size situations. Based on these findings, it is suggested that the POV is not a replacement for more complex analysis methods, but rather, a supplement to them. POV is ideal for preliminary analysis due to the ease of implementation, the simplicity of interpretation, and the lack of dependency on statistical analysis packages or statistical knowledge.
ContributorsLittle, David John (Author) / Borror, Connie (Thesis advisor) / Montgomery, Douglas C. (Committee member) / Broatch, Jennifer (Committee member) / Arizona State University (Publisher)
Created2015