A GLM approach to quantal response models for mixtures

Research output: Contribution to journalArticle

Abstract

Quantal response models for the combination of two different stimuli are considered as exponential family regression models. In the most general cases the models are nonlinear in the sense that there is no link to a linear predictor. Examples include probit models for correlated independent action and logit models for similar action. Parameters for spontaneous response are included. An extensive series of examples shows that these models can be easily fitted to real data using standard statistical software. Results include deviance statistics for goodness of fit, as well as maximum likelihood estimates of EC50s, relative potencies, and mixing parameters, together with their standard deviations. Likelihood ratio statistics for testing special models are easily computed, facilitating the analysis of complex data sets. Deviance residuals help detect lack of fit and individual outliers.

Original languageEnglish (US)
Pages (from-to)911-928
Number of pages18
JournalBiometrics
Volume48
Issue number3
StatePublished - 1992
Externally publishedYes

Fingerprint

Likelihood Functions
Deviance
Software
Logistic Models
Lack of Fit
Probit Model
Logit Model
Statistical Software
Likelihood Ratio Statistic
Exponential Family
statistics
Goodness of fit
Maximum Likelihood Estimate
Model
Standard deviation
Outlier
Predictors
Regression Model
Statistics
logit analysis

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Agricultural and Biological Sciences (miscellaneous)
  • Applied Mathematics
  • Statistics and Probability
  • Public Health, Environmental and Occupational Health

Cite this

A GLM approach to quantal response models for mixtures. / Cox, Christopher.

In: Biometrics, Vol. 48, No. 3, 1992, p. 911-928.

Research output: Contribution to journalArticle

@article{a3d2fc20218b4adba55dfabd7db2f54c,
title = "A GLM approach to quantal response models for mixtures",
abstract = "Quantal response models for the combination of two different stimuli are considered as exponential family regression models. In the most general cases the models are nonlinear in the sense that there is no link to a linear predictor. Examples include probit models for correlated independent action and logit models for similar action. Parameters for spontaneous response are included. An extensive series of examples shows that these models can be easily fitted to real data using standard statistical software. Results include deviance statistics for goodness of fit, as well as maximum likelihood estimates of EC50s, relative potencies, and mixing parameters, together with their standard deviations. Likelihood ratio statistics for testing special models are easily computed, facilitating the analysis of complex data sets. Deviance residuals help detect lack of fit and individual outliers.",
author = "Christopher Cox",
year = "1992",
language = "English (US)",
volume = "48",
pages = "911--928",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - A GLM approach to quantal response models for mixtures

AU - Cox, Christopher

PY - 1992

Y1 - 1992

N2 - Quantal response models for the combination of two different stimuli are considered as exponential family regression models. In the most general cases the models are nonlinear in the sense that there is no link to a linear predictor. Examples include probit models for correlated independent action and logit models for similar action. Parameters for spontaneous response are included. An extensive series of examples shows that these models can be easily fitted to real data using standard statistical software. Results include deviance statistics for goodness of fit, as well as maximum likelihood estimates of EC50s, relative potencies, and mixing parameters, together with their standard deviations. Likelihood ratio statistics for testing special models are easily computed, facilitating the analysis of complex data sets. Deviance residuals help detect lack of fit and individual outliers.

AB - Quantal response models for the combination of two different stimuli are considered as exponential family regression models. In the most general cases the models are nonlinear in the sense that there is no link to a linear predictor. Examples include probit models for correlated independent action and logit models for similar action. Parameters for spontaneous response are included. An extensive series of examples shows that these models can be easily fitted to real data using standard statistical software. Results include deviance statistics for goodness of fit, as well as maximum likelihood estimates of EC50s, relative potencies, and mixing parameters, together with their standard deviations. Likelihood ratio statistics for testing special models are easily computed, facilitating the analysis of complex data sets. Deviance residuals help detect lack of fit and individual outliers.

UR - http://www.scopus.com/inward/record.url?scp=0026629751&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026629751&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0026629751

VL - 48

SP - 911

EP - 928

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 3

ER -