What guides a researcher when deciding between using either linear, logistic, or cox proportional hazards regression as an analysis tool?
a. the types of predictors (binary, multi-categorical, or continuous) that may be used in the regression model(s).
b. the number of observations in the dataset being analyzed.
c. the outcome variable type (continuous, binary, or time –to-event) for the particular analyses
utilizing the regression model(s).
d. whether or not the researcher wants to investigate confounding.
the generic formulation of a multiple regression model including age (x1=age in years), sex (x2= 1 if female, 0 if male), and smoking status (x3 = 1 if smoker, and 0 if non-smoker) as predictors is as follows:
= + + + where lhs = "left hand side", and intercept = ln