| Case-control studies can be used to investigate the relationship between a disease and potential risk factor(s). The logistic regression analysis is one of the analytical tools used in case-control studies. There are two types of logistic regression models that can be used in case-control studies. The model for the log odds of exposure fits the case-control sampling scheme which is disease-dependent. The model for the log odds of disease contradicts the case-control sampling scheme. However, Prentice and Pyke provided the theoretical justification for using the model for the log odds of disease in case-control studies. The primary aim of this thesis is to compare the coefficients that are related to disease or exposure, as well as, their standard errors in the two types of logistic regression models. Some suggestions for future research directions are provided at the end. |
