Regression diagnostics check assumptions and influential observations in a fitted regression function. Residual-versus-fitted plots can reveal omitted mean structure or nonconstant variance; a quantile-quantile plot checks a specified error distribution. Regression leverage measures unusual predictor configurations, and Cook's distance combines leverage and residual size to measure coefficient sensitivity. Independence may require checking collection order and the study design in addition to residual plots.
Articles by others on the same topic
Regression diagnostics refers to a set of techniques used to assess the validity of a regression model, ensure that the assumptions of the regression analysis are met, and identify potential issues that might affect the model's performance. These diagnostics help researchers and analysts evaluate the quality of their model and its predictions by checking various aspects of the model fit and residuals.