We investigate the use of smoothing splines in logistic regression to estimate the covariate values that yield a fixed response probability, eg. LC50 or LD50. We develop an algorithm for a monotonic spline fit and approximate the resulting probability estimates and the fixed-response covariates. We illustrate our algorithm on data sets from studies of genetic spatial diversity.
Keywords: smoothing splines, logistic regression
Corresponding author: E-mail : cast@kmitl.ac.th
Kittichotipanit, N. ., & Jernigan, R. W. . (2018). An Algorithm to Approximate the Fixed-Response Covariates in Logistic Regression Using Smoothing Splines. CURRENT APPLIED SCIENCE AND TECHNOLOGY, 410-419.
