Added-variable plots are useful for a variety of data-analytic purposes but can be seriously misleading when used to investigate curvature and predictor transformations in linear regression, unless the predictors are independent.
Bibliographical noteFunding Information:
Research for this article was supported in part by National Science Foundation grants DMS 92-424 13 and DUE 93-54678.
Copyright 2017 Elsevier B.V., All rights reserved.
- Component-plus-residual plots
- Influential observations
- Partial residual plots
- Predictor transformations