ABSTRACT
In this chapter, we consider simultaneous confidence bands for logistic regression analysis . The key idea is to combine the large sample asymptotic normality of the maximum likelihood estimators of the regression coefficients with the results for the normal-error linear regression models derived in the previous chapters. The methods given in this chapter are clearly applicable to other generalized linear models, linear mixed-effects models and generalized linear mixed-effects models for which asymptotic normality such as those given in (8.16), (8.21) and (8.28) below holds (cf. Pinheiro and Bates, 2000, and McCulloch and Searle, 2001). The logistic regression model is used mainly for the purpose of illustration.
