Identifying influential multinomial observations by perturbation

DOI10.1016/j.csda.2005.04.023zbMath1445.62172MaRDI QIDQ959363

B. E. Eshmatov

Publication date: 11 December 2008

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://pure.rug.nl/ws/files/2850682/2006ComputStatDataAnalNyangoma.pdf

zbMATH Keywords

perturbation; influence; diagnostics; maximum likelihood estimate; likelihood displacement; conditional model

Mathematics Subject Classification ID

62J05: Linear regression; mixed models

62P10: Applications of statistics to biology and medical sciences; meta analysis

62J20: Diagnostics, and linear inference and regression

Related Items

Influence analysis in truncated distributions, Some measures of robustness for unbiased estimators in one-parameter natural exponential families with quadratic variance function

Uses Software

• alr3

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Some diagnostic measures in discriminant analysis
• Logistic regression diagnostics
• Confidence regions for multinomial parameters
• Generalized Linear Model Diagnostics Using the Deviance and Single Case Deletions
• Detection of Influential Observation in Linear Regression
• Influential Observations in Linear Regression
• Local influence in principal components analysis
• Theory & Methods: Detection of influential observations in nonlinear reproductive dispersion models
• Assessing Influence in Regression Analysis with Censored Data
• Diagnostics in Linear Discriminant Analysis
• Residuals for multinomial models
• Linear Statistical Inference and its Applications
• A New Proof of the Pearson-Fisher Theorem