On two methods of identifying influential sets of observations

DOI10.1016/0167-7152(88)90057-0MaRDI QIDQ1116238zbMATH OpenOpenAlexFDO

Authors Subir Ghosh

Publication date 1988

Published in Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0167-7152(88)90057-0

zbMATH Keywords

Cook's measurefittinginfluential sets of observationslinear modelspredictionrobustnessunavailable observations

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Factorial statistical designs (62K15)

Review text

Two new measures are proposed to identify influential sets of observations at the design stage in view of prediction and fitting. A relationship is established between one of the proposed measures and the Cook's measure [see \textit{R. D. Cook}, Technometrics 19, 15-18 (1977; Zbl 0371.62096)] at the inference stage.

Recommendations

• A STEPWISE APPROACH FOR DETECTION OF INFLUENTIAL OBSERVATIONS
• Identifying influential multinomial observations by perturbation
• Procedures for the identification of multiple influential observations using local influence
• Identification of influential observations on total least squares estimates
• Detecting influential observations for estimated probabilities in multiple discriminant analysis
• A note on the relationship between influential observations and model selection

Cites work

• Characterizations of an Empirical Influence Function for Detecting Influential Cases in Regression
• scientific article; zbMATH DE number 3899977 (Why is no real title available?)
• scientific article; zbMATH DE number 3176492 (Why is no real title available?)
• scientific article; zbMATH DE number 3675167 (Why is no real title available?)
• Influential Observations and Outliers in Regression
• Influential observations, high leverage points, and outliers in linear regression

Cited in

(14)

• Deletion, augmentation and principal predictors
• Factorial and response surface designs robust to missing observations
• Information complexity criteria for detecting influential observations in dynamic multivariate linear models using the genetic algorithm
• A unifying representation of some case-deletion influence measures in univariate and multivariate linear regression
• Influential observations in view of design and inference
• scientific article; zbMATH DE number 4169897 (Why is no real title available?)
• scientific article; zbMATH DE number 482235 (Why is no real title available?)
• A STEPWISE APPROACH FOR DETECTION OF INFLUENTIAL OBSERVATIONS
• Measuring influence of observations in predict1on and estimation for central composite designs
• ASSESSMENT OF INFLUENCE OF INDIVIDUAL OBSERVATIONS ON PREDICTION MEAN SQUARE ERRORS IN VARIABLE SELECTION PROBLEMS
• Graphical and Numerical Methods for Detecting Influential Observations in Complex Bingham Data
• Leverage and subset efficiencies in regression
• Properties of selected subset diagnostics in regression
• Efficiency comparisons in linear inference

This page was built for publication: On two methods of identifying influential sets of observations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1116238)