Logistic Regression

This chapter investigates whether or not the probability of death depends upon two further variables, degree of exposure to nitrous dioxide, and exposure time. It analyses the mice exposure data and standardizes each set of explanatory variables, log degree of exposure and log exposure time, by subtracting the sample mean and then dividing by the sample standard deviation, for each set separately. The chapter attempts to fit the main effects model. Both the intercept and the slope of this model are weakly significantly different from zero. The chapter concludes that degree of exposure and exposure time interact to create a strong relationship with the probability of death.