Date of Award
Master of Science
Dr. Neil Klar
Dr. Yun-Hee Choi
The purpose of this research was twofold. The first objective was to assess the quality of modern cross-sectional ecological studies with a bibliometric review. The second objective was to investigate via simulation study the reliability of common ecological regression models for analysing count data.
The bibliometric review found that the quality and areas of application of the ecological literature is quite diverse. However, a large proportion of studies exhibited poor statistical practice and provided insufficient amounts of justification and information.
Linear, weighted linear, Poisson, and negative binomial regression were included in the simulation study based on their prevalence in the bibliometric review. The Poisson and negative binomial models had overly-liberal Type I error rates when faced with overdispersion or small samples respectively. Linear and weighted linear regression had highly robust Type I error rates. For all models, power decreased primarily as a function of overdispersion.
Dufault, Brenden T., "EVALUATING ECOLOGICAL STUDIES IN EPIDEMIOLOGY" (2009). Digitized Theses. 4007.