Logistic regression is a valuable statistical tool used to model the probability of a binary response variable as a function of one or more input variables. The goal of this thesis research is to develop a better understanding of how the coefficients of a logistic regression model influence the probability of a response. Typically, the odds ratio is used for this, but this research focuses on the steepness of logistic curve near the median quantile. In order to study this, a web application using R Shiny was developed to simulate a logistic regression function based on a single continuous input variable. The web application allows a variety of inputs to be manipulated, including sample size, noise structure, amount of noise, and actual parameter values. An example using the NASA O-Ring data is illustrated as motivation and discussion.
Industrial and Systems Engineering (MS)
Department, Program, or Center
Industrial and Systems Engineering (KGCOE)
Kist, Michael J., "Logistic Regression Slope Study" (2017). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus