Identifiability of Models for Multiple Diagnostic Testing in the Absence of a Gold Standard

We discuss the issue of identifiability of models for multiple dichotomous diagnostic tests in the absence of a gold standard (GS) test. Data arise as multinomial or product-multinomial counts depending upon the number of populations sampled. Models are generally posited in terms of population preva...

Full description

Saved in:
Bibliographic Details
Published in:Biometrics 2010-09, Vol.66 (3), p.855-863
Main Authors: Jones, Geoffrey, Johnson, Wesley O., Hanson, Timothy E., Christensen, Ronald
Format: Article
Language:English
Subjects:
Algebra
BIOMETRIC METHODOLOGY
Biometrics
Biometry - methods
Computer Simulation
Correlated tests
Degrees of freedom
Diagnostic tests
Diagnostic Tests, Routine - methods
Diagnostic Tests, Routine - standards
Diagnostic Tests, Routine - statistics & numerical data
Disease models
Epidemiologic Measurements
Gold standard
Humans
Identifiability
Jacobians
Latent class model
Mathematical vectors
Medical diagnostic tests
Modeling
Models, Statistical
Parametric models
Prevalence
Sensitivity
Sensitivity and Specificity
Specificity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We discuss the issue of identifiability of models for multiple dichotomous diagnostic tests in the absence of a gold standard (GS) test. Data arise as multinomial or product-multinomial counts depending upon the number of populations sampled. Models are generally posited in terms of population prevalences, test sensitivities and specificities, and test dependence terms. It is commonly believed that if the degrees of freedom in the data meet or exceed the number of parameters in a fitted model then the model is identifiable. Goodman (1974, Biometrika 61, 215-231) established that this was not the case a long time ago. We discuss currently available models for multiple tests and argue in favor of an extension of a model that was developed by Dendukuri and Joseph (2001, Biometrics 57, 158-167). Subsequently, we further develop Goodman's technique, and make geometric arguments to give further insight into the nature of models that lack identifiability. We present illustrations using simulated and real data.
ISSN:0006-341X
1541-0420
DOI:10.1111/j.1541-0420.2009.01330.x