A Double-Penalized Estimator to Combat Separation and Multicollinearity in Logistic Regression

• Published in: Mathematics (Basel) Vol. 10; no. 20; p. 3824
• Main Authors: Guan, Ying, Fu, Guang-Hui
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.10.2022
• Subjects: Algorithms; Bias; Binary data; Breast cancer; double-penalized likelihood estimator; Estimates; Linear models (Statistics); Linear regression models; logF-type penalty; Logistic regression; Mathematical research; Maximum likelihood estimates; Medical research; Methods; multicollinearity; Prediction models; Predictions; Probability; Regression; Separation; Variables; United States

When developing prediction models for small or sparse binary data with many highly correlated covariates, logistic regression often encounters separation or multicollinearity problems, resulting serious bias and even the nonexistence of standard maximum likelihood estimates. The combination of separ...