A novel method for evaluating an interaction effect of correlated continuous covariates in a linear model

Interaction effect is an important scientific interest for many areas of research. Common approach for investigating the interaction effect of two continuous covariates on a response variable is through a cross-product term in multiple linear regression. In epidemiological studies, the two-way analysis of variance (ANOVA) type of method has also been utilized to examine the interaction effect by replacing the continuous covariates with their discretized levels. However, the implications of model assumptions of either approach have not been examined and the statistical validation has only focused on the general method, not specifically for the interaction effect.^ In this dissertation, we investigated the validity of both approaches based on the mathematical assumptions for non-skewed data. We showed that linear regression may not be an appropriate model when the interaction effect exists because it implies a highly skewed distribution for the response variable. We also showed that the normality and constant variance assumptions required by ANOVA are not satisfied in the model where the continuous covariates are replaced with their discretized levels. Therefore, naïve application of ANOVA method may lead to an incorrect conclusion. ^ Given the problems identified above, we proposed a novel method modifying from the traditional ANOVA approach to rigorously evaluate the interaction effect. The analytical expression of the interaction effect was derived based on the conditional distribution of the response variable given the discretized continuous covariates. A testing procedure that combines the p-values from each level of the discretized covariates was developed to test the overall significance of the interaction effect. According to the simulation study, the proposed method is more powerful then the least squares regression and the ANOVA method in detecting the interaction effect when data comes from a trivariate normal distribution. The proposed method was applied to a dataset from the National Institute of Neurological Disorders and Stroke (NINDS) tissue plasminogen activator (t-PA) stroke trial, and baseline age-by-weight interaction effect was found significant in predicting the change from baseline in NIHSS at Month-3 among patients received t-PA therapy.^

The illness experiences of African Americans residing in an inner city community, Houston, Texas

This dissertation documents health and illness in the context of daily life circumstances and structural conditions faced by African American families living in Clover Heights (pseudonym), an inner city public housing project in the Third Ward, Houston, Texas. Drawing from Kleinman's (1980) model of culturally defined health care systems and using the holistic-content approach to narrative analysis (Lieblich, Tuval- Mashiach, & Zilber, 1998) the purpose of this research was to explore the ways in which social and health policy, economic mobility, the inner city environment, and cultural beliefs intertwined with African American families' health related ideas, behaviors, and practices. I recruited six families using a convenience sampling method (Schensul, Schensul, & LeCompte, 1999) and followed them for fourteen months (2010–2011). Family was defined as a household unit, or those living in the same residence, short or long-term. Single, African American women ranging in age from 29–80 years headed all families. All but one family included children or grandchildren 18 years of age and younger, or children or other relative 18 years of age and older. I also recruited six residents with who I became acquainted over the course of the project. I collected data using traditional ethnographic methods including participant-observation, archive review, field notes, mapping, free-listing, in-depth interviews, and life history interviews. ^ Doing ethnography afforded the families who participated in this project the freedom to construct their own experiences of health and illness. My role centered on listening to, learning from, and interpreting participants' narratives, exploring similarities and differences within and across families' experiences. As the research progressed, a pattern concerning diagnosis and pharmacotherapy for children's behavioral and emotional problems, particularly attention-deficit hyperactivity disorder (ADHD) and pediatric bipolar disorder (PBD), emerged from my formal interactions with participants and my informal interactions with residents. The findings presented in this dissertation document this pattern, focusing on how mothers and families interpreted, organized, and ascribed meaning to their experiences of ADHD and PBD. ^ In the first manuscript presented here, I documented three mothers' narrative constructions of a child's diagnosis with and pharmacotherapy for ADHD or PBD. Using Gergen's (1997) relational perspective I argued that mothers' knowledge and experiences of ADHD and PBD were not individually constructed, but were linguistically and discursively constituted through various social interactions and relationships, including family, spirituality and faith, community norms, and expert systems of knowledge. Mothers' narratives revealed the complexity of children's behavioral and emotional problems, the daily trials of living through these problems, how they coped with adversity and developed survival strategies, and how they interacted with various institutional authorities involved in evaluating, diagnosing, and encouraging pharmaceutical intervention for children's behavior. The findings highlight the ways in which mothers' social interactions and relationships introduced a scientific language and discourse for explaining children's behavior as mental illness, the discordances between expert systems of knowledge and mothers' understandings, and how discordances reflected mothers' ‘microsources of power’ for producing their own stories and experiences. ^ In the second manuscript presented here, I documented the ways in which structural factors, including gender, race/ethnicity, and socioeconomic status, coupled with a unique cultural and social standpoint (Collins, 1990/2009) influenced the strategies this group of African American mothers employed to understand and respond to ADHD or PBD. The most salient themes related to mother-child relationships coalesced around mothers' beliefs about the etiology of ADHD and PBD, ‘conceptualizing responsibility,’ and ‘protection-survival.’ The findings suggest that even though mothers' strategies varied, they were in pursuit of a common goal. Mothers' challenged the status quo, addressing children's behavioral and emotional problems in the ways that made the most sense to them, specifically protecting their children from further marginalization in society more so than believing these were the best options for their children.^

Instrumental variable method for the causal relationship between soluble receptor for advanced glycation end-products (sRAGE) and risk of pancreatic cancer

This thesis project is motivated by the potential problem of using observational data to draw inferences about a causal relationship in observational epidemiology research when controlled randomization is not applicable. Instrumental variable (IV) method is one of the statistical tools to overcome this problem. Mendelian randomization study uses genetic variants as IVs in genetic association study. In this thesis, the IV method, as well as standard logistic and linear regression models, is used to investigate the causal association between risk of pancreatic cancer and the circulating levels of soluble receptor for advanced glycation end-products (sRAGE). Higher levels of serum sRAGE were found to be associated with a lower risk of pancreatic cancer in a previous observational study (255 cases and 485 controls). However, such a novel association may be biased by unknown confounding factors. In a case-control study, we aimed to use the IV approach to confirm or refute this observation in a subset of study subjects for whom the genotyping data were available (178 cases and 177 controls). Two-stage IV method using generalized method of moments-structural mean models (GMM-SMM) was conducted and the relative risk (RR) was calculated. In the first stage analysis, we found that the single nucleotide polymorphism (SNP) rs2070600 of the receptor for advanced glycation end-products (AGER) gene meets all three general assumptions for a genetic IV in examining the causal association between sRAGE and risk of pancreatic cancer. The variant allele of SNP rs2070600 of the AGER gene was associated with lower levels of sRAGE, and it was neither associated with risk of pancreatic cancer, nor with the confounding factors. It was a potential strong IV (F statistic = 29.2). However, in the second stage analysis, the GMM-SMM model failed to converge due to non- concaveness probably because of the small sample size. Therefore, the IV analysis could not support the causality of the association between serum sRAGE levels and risk of pancreatic cancer. Nevertheless, these analyses suggest that rs2070600 was a potentially good genetic IV for testing the causality between the risk of pancreatic cancer and sRAGE levels. A larger sample size is required to conduct a credible IV analysis.^