A simple graphic for assessing influence in regression
- 1 June 1986
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 24 (2) , 121-134
- https://doi.org/10.1080/00949658608810895
Abstract
The leverage-residual plot (L–R plot) is a graphical display of the leverage and residual values for each case in a regression which facilitates the examination of the relative influences of cases under different influence measures. This plot is also useful in attributing the cause of high influence in a case to its leverage, its residual, or their combined effect. The ability to analyze and compare the various single-case influence measures is a by-product of the L-R plot.Keywords
This publication has 11 references indexed in Scilit:
- Outlier..........sTechnometrics, 1983
- [Outlier..........s]: DiscussionTechnometrics, 1983
- A Predictive View of the Detection and Characterization of Influential Observations in Regression AnalysisJournal of the American Statistical Association, 1983
- The Use of Bounded-Influence Regression in Data Analysis: Theory, Computation, and GraphicsPublished by Springer Nature ,1983
- Influential Observations and Outliers in RegressionTechnometrics, 1981
- Regression DiagnosticsPublished by Wiley ,1980
- Influential Observations in Linear RegressionJournal of the American Statistical Association, 1979
- The Hat Matrix in Regression and ANOVAThe American Statistician, 1978
- Detection of Influential Observation in Linear RegressionTechnometrics, 1977
- Residuals and Their Variance PatternsTechnometrics, 1972