Logistic regression, also known as logit regression, or logit model is a probabilistic linear model for dichotomous data. The response variable is a binary variable (nominal variable), which means the variable has two categories or two values; True vs. False, or $1$ vs. $0$, or success vs. failure, with the probabilities of $\pi$ and $1-\pi$, respectively. Thus, the response variable follows a binomial distribution written as
$$y \sim B(\eta,\pi)\text{,}$$where $\eta$ is the binomial denominator, which is for a binary variable $0$ or $1$ and $\pi$ is the probability of success.
For this part we rely on the following modules, libraries, and packages:
Citation
The E-Learning project SOGA-Py was developed at the Department of Earth Sciences by Annette Rudolph, Joachim Krois and Kai Hartmann. You can reach us via mail by soga[at]zedat.fu-berlin.de.
Please cite as follow: Rudolph, A., Krois, J., Hartmann, K. (2023): Statistics and Geodata Analysis using Python (SOGA-Py). Department of Earth Sciences, Freie Universitaet Berlin.