Logistic Regression Diagnostics
Daryl Pregibon · The Annals of Statistics · 1981
A maximum likelihood fit of a logistic regression model (and other similar models) is extremely sensitive to outlying responses and extreme points in the design space. We develop diagnostic measures to aid the analyst in detecting such observations and in quantifying their effect on various aspects of the maximum likelihood fit. The elements of the fitting process which constitute the usual output (parameter estimates, standard errors, residuals, etc.) will be used for this purpose. With a properly designed computing package for fitting the usual maximum-likelihood model, the diagnostics are essentially "free for the asking." In particular, good data analysis for logistic regression models need not be expensive or time-consuming.
Cited by 1,290 works. doi:10.1214/aos/1176345513 Open-access PDF
Authors
References
- Generalized Linear Models
- Regression Diagnostics -- Identifying Influential Data and Sources of Collinearity
- Data Analysis and Regression.
- Detection of Influential Observation in Linear Regression
- The Hat Matrix in Regression and ANOVA
- Influential Observations in Linear Regression
- Goodness of Link Tests for Generalized Linear Models
- Finding the Outliers that Matter
- THE ESTIMATION FROM INDIVIDUAL RECORDS OF THE RELATIONSHIP BETWEEN DOSE AND QUANTAL RESPONSE
- Linear Regression Diagnostics