Confidence intervals for parameters of two diagnostic tests in the absence of a gold standard

We derive a profile-likelihood confidence interval and a score based confidence interval to estimate the population prevalences, test sensitivities, and test specificities of two conditionally independent diagnostic tests when no gold standard is available. We are motivated by a real-data example on the study of the properties for two fallible diagnostic tests for bovine immunodeficiency virus. We compare the coverage and average width of two new intervals with an interval based on the asymptotic normality of the maximum likelihood estimator and a Bayesian interval estimator via Monte Carlo simulation. We determine that for the parameter configurations considered here, the profile-likelihood, score, and Bayesian intervals all perform adequately in terms of coverage, but overall, the profile-likelihood interval performs best in terms of yielding at least nominal coverage with minimum expected width.

[1]  K A Orr,et al.  Estimation of sensitivity and specificity of two diagnostics tests for bovine immunodeficiency virus using Bayesian techniques. , 2003, Preventive veterinary medicine.

[2]  L. Joseph,et al.  Bayesian estimation of disease prevalence and the parameters of diagnostic tests in the absence of a gold standard. , 1995, American journal of epidemiology.

[3]  I A Gardner,et al.  Estimation of diagnostic-test sensitivity and specificity through Bayesian modeling. , 2005, Preventive veterinary medicine.

[4]  L. Joseph,et al.  Bayesian Approaches to Modeling the Conditional Dependence Between Multiple Diagnostic Tests , 2001, Biometrics.

[5]  W O Johnson,et al.  Screening without a "gold standard": the Hui-Walter paradigm revisited. , 2001, American journal of epidemiology.

[6]  Kevin Schwartzman,et al.  Bayesian modelling of tuberculosis clustering from DNA fingerprint data , 2008, Statistics in medicine.

[7]  ScienceDirect.  Computational statistics & data analysis , 1983 .

[8]  S. Walter,et al.  Estimating the error rates of diagnostic tests. , 1980, Biometrics.

[9]  John W Seaman,et al.  Bayesian sample‐size determination for inference on two binomial populations with no gold standard classifier , 2005, Statistics in medicine.

[10]  T. Tony Cai,et al.  Confidence Intervals for a binomial proportion and asymptotic expansions , 2002 .

[11]  Nandini Dendukuri,et al.  Bayesian Sample Size Determination for Prevalence and Diagnostic Test Studies in the Absence of a Gold Standard Test , 2004, Biometrics.

[12]  W. Johnson,et al.  Evaluation of bluetongue virus diagnostic tests in free-ranging bighorn sheep. , 1998, Preventive veterinary medicine.

[13]  Douglas G. Bonett,et al.  Estimating the ratio of two Poisson rates , 2000 .

[14]  Ian A Gardner,et al.  "TAGS", a program for the evaluation of test accuracy in the absence of a gold standard. , 2002, Preventive veterinary medicine.

[15]  W. Johnson,et al.  Bayesian analysis of risk factors for anovulation , 2004, Statistics in medicine.

[16]  B. Craig,et al.  Estimating disease prevalence in the absence of a gold standard , 2002, Statistics in medicine.

[17]  Wesley O Johnson,et al.  Sample size determination for estimation of the accuracy of two conditionally independent tests in the absence of a gold standard. , 2005, Preventive veterinary medicine.

[18]  L. Barker,et al.  A Comparison of Nine Confidence Intervals for a Poisson Parameter When the Expected Number of Events is ≤ 5 , 2002 .

[19]  Dean M. Young,et al.  Confidence intervals for a binomial parameter based on binary data subject to false-positive misclassification , 2006, Comput. Stat. Data Anal..

[20]  A. Agresti,et al.  Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions , 1998 .

[21]  W O Johnson,et al.  Estimation of sensitivity and specificity of diagnostic tests and disease prevalence when the true disease state is unknown. , 2000, Preventive veterinary medicine.