Measures of relative model fit

Alan Agresti; Brian Caffo

doi:10.1016/S0167-9473(01)00054-8

Measures of relative model fit

Alan Agresti, Brian Caffo

Research output: Contribution to journal › Article › peer-review

10 Scopus citations

Abstract

Most software for statistical model fitting reports the value of the maximized log likelihood function, but the numerical value is difficult to interpret because of its log scale, its dependence on the sample size, and the possible omission of constants. A sample-size-scaled version of the likelihood function summarizes the model fit. A related index uses the mean of the contributions to the likelihood function. The ratio or difference of either index for two models is a summary measure of relative model fit. We discuss these measures and briefly consider interval estimation for them.

Original language	English (US)
Pages (from-to)	127-136
Number of pages	10
Journal	Computational Statistics and Data Analysis
Volume	39
Issue number	2
DOIs	https://doi.org/10.1016/S0167-9473(01)00054-8
State	Published - Apr 28 2002
Externally published	Yes

Keywords

AIC
Deviance
Discrete data
Dissimilarity
Likelihood function
Non-nested models

ASJC Scopus subject areas

Statistics and Probability
Computational Mathematics
Computational Theory and Mathematics
Applied Mathematics

Access to Document

10.1016/S0167-9473(01)00054-8

Cite this

@article{eab8c7c20a5c417d8f098f69edd8bca8,

title = "Measures of relative model fit",

abstract = "Most software for statistical model fitting reports the value of the maximized log likelihood function, but the numerical value is difficult to interpret because of its log scale, its dependence on the sample size, and the possible omission of constants. A sample-size-scaled version of the likelihood function summarizes the model fit. A related index uses the mean of the contributions to the likelihood function. The ratio or difference of either index for two models is a summary measure of relative model fit. We discuss these measures and briefly consider interval estimation for them.",

keywords = "AIC, Deviance, Discrete data, Dissimilarity, Likelihood function, Non-nested models",

author = "Alan Agresti and Brian Caffo",

note = "Funding Information: This research was partially supported by grants from NSF and NIH. The authors acknowledge helpful comments from referees, such as pointing out the econometric literature on tests comparing models.",

year = "2002",

month = apr,

day = "28",

doi = "10.1016/S0167-9473(01)00054-8",

language = "English (US)",

volume = "39",

pages = "127--136",

journal = "Computational Statistics and Data Analysis",

issn = "0167-9473",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Measures of relative model fit

AU - Agresti, Alan

AU - Caffo, Brian

N1 - Funding Information: This research was partially supported by grants from NSF and NIH. The authors acknowledge helpful comments from referees, such as pointing out the econometric literature on tests comparing models.

PY - 2002/4/28

Y1 - 2002/4/28

N2 - Most software for statistical model fitting reports the value of the maximized log likelihood function, but the numerical value is difficult to interpret because of its log scale, its dependence on the sample size, and the possible omission of constants. A sample-size-scaled version of the likelihood function summarizes the model fit. A related index uses the mean of the contributions to the likelihood function. The ratio or difference of either index for two models is a summary measure of relative model fit. We discuss these measures and briefly consider interval estimation for them.

AB - Most software for statistical model fitting reports the value of the maximized log likelihood function, but the numerical value is difficult to interpret because of its log scale, its dependence on the sample size, and the possible omission of constants. A sample-size-scaled version of the likelihood function summarizes the model fit. A related index uses the mean of the contributions to the likelihood function. The ratio or difference of either index for two models is a summary measure of relative model fit. We discuss these measures and briefly consider interval estimation for them.

KW - AIC

KW - Deviance

KW - Discrete data

KW - Dissimilarity

KW - Likelihood function

KW - Non-nested models

UR - http://www.scopus.com/inward/record.url?scp=0037188232&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037188232&partnerID=8YFLogxK

U2 - 10.1016/S0167-9473(01)00054-8

DO - 10.1016/S0167-9473(01)00054-8

M3 - Article

AN - SCOPUS:0037188232

SN - 0167-9473

VL - 39

SP - 127

EP - 136

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

IS - 2

ER -

Measures of relative model fit

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this