[size=1em]when people use logistic regression for modeling response of rare occurence, one practice widely accepted is oversampling or undersampling to model these rare events. What is the benefit? The model  should be the same, except the intercept. Or if anyone can share the following two papers with me, it will be really appreciated.
[size=1em]1.Scott, A. J.and Wild, C. J. (1986) Fitting logistic models under case-control or choice based sampling Journal of the Royal Statistical Society. Series B, 48,170-182.
2. Scott, A. J.and Wild, C. J. (1997) Fitting logistic models to case-control data by Maximum Likelihood, Biometrika 84, 57-61.