Using Cook's distance in polytomous logistic regression Journal Articles

abstract

• The previously unknown asymptotic distribution of Cook's distance in polytomous logistic regression is established as a linear combination of independent chi‐square random variables with one degree of freedom. An exhaustive approach to the analysis of influential covariates is developed and a new measure for the accuracy of predictions based on such a distribution is provided. Two examples with real data sets (one with continuous covariates and the other with both qualitative and quantitative covariates) are presented to illustrate the approach developed.

authors

• Martin Apaolaza, Niran

status

• published 

publication date

• February 2015

has subject area

• 0104 Statistics (FoR)
• 1701 Psychology (FoR)
• Analysis of Variance (MeSH)
• Logistic Models (MeSH)
• Psychometrics (MeSH)
• Social Sciences Methods (Science Metrix)
• Statistical Distributions (MeSH)

published in

• British Journal of Mathematical and Statistical Psychology  Journal

keywords

• Analysis of Variance
• Cook's distance
• Logistic Models
• Psychometrics
• Statistical Distributions
• multinomial sampling
• polytomous regression model

Digital Object Identifier (DOI)

• 10.1111/bmsp.12036

PubMed ID

• 24712549

start page

• 84

end page

• 115

volume

• 68

issue

• 1