Confidence intervals for proportion difference from two independent partially validated series

Abstract

Partially validated series are common when a gold-standard test is too expensive to be applied to all subjects, and hence a fallible device is used accordingly to measure the presence of a characteristic of interest. In this article, confidence interval construction for proportion difference between two independent partially validated series is studied. Ten confidence intervals based on the method of variance estimates recovery (MOVER) are proposed, with each using the confidence limits for the two independent binomial proportions obtained by the asymptotic, Logit-transformation, Agresti–Coull and Bayesian methods. The performances of the proposed confidence intervals and three likelihood-based intervals available in the literature are compared with respect to the empirical coverage probability, confidence width and ratio of mesial non-coverage to non-coverage probability. Our empirical results show that (1) all confidence intervals exhibit good performance in large samples; (2) confidence intervals based on MOVER combining the confidence limits for binomial proportions based on Wilson, Agresti–Coull, Logit-transformation, Bayesian (with three priors) methods perform satisfactorily from small to large samples, and hence can be recommended for practical applications. Two real data sets are analysed to illustrate the proposed methods.

Keywords

Bayesian confidence interval proportion difference partially validated series method of variance estimates recovery

Get full access to this article

View all access options for this article.

References

Bross

. Misclassification in 2 × 2 tables. Biometrics 1954; 10: 478–486.

Tenenbein

. A double sampling scheme for estimating from binomial data with misclassifications. J Am Stat Assoc 1970; 65: 1350–1361.

Tang

Qiu

Poon

. Test procedures for disease prevalence with partially validated data. J Biopharm Stat 2012; 22: 368–386.

Tenenbein

. A double sampling scheme for estimating form binomial data with misclassifications: sample size determination. Biometrics 1971; 27: 935–944.

Tenenbein

. A double sampling scheme for estimating from misclassified multinomial data with applications to sampling inspection. Technometrics 1972; 14: 187–202.

Moors

JJA

van der Genugten

Strijbosch

LWG

. Repeated audit controls. Stat Neelandica 2000; 54: 3–13.

Boesea

Youngb

Stameyb

. Confidence intervals for a binomial parameter based on binary data subject to false-positive misclassification. Comput Stat Data Anal 2006; 50: 3369–3385.

Lee

Byun

. A Bayesian approach to obtain confidence intervals for binomial proportion in a double sampling scheme subject to false-positive misclassification. J Korean Stat Soc 2008; 37: 393–403.

Lee

. Bayesian confidence intervals of proportion with misclassified binary data. Journal of the Korean Statistical Society 2013; 42(3): 291–299.

10.

Tang

Qiu

Poon

. Confidence interval construction for disease prevalence based on partial validation series. Comput Stat Data Anal 2012; 56: 1200–1220.

11.

Qiu SF, Poon WY and Tang ML. Sample size determination for disease prevalence studies with partially validated data. Stat Methods Med Res. Epub ahead of print 28 February 2012. DOI: 10.1177/0962280212439576.

12.

Geng

Asano

. Bayesian estimation methods for categorical data with misclassification. Commun Stat: Theory Methods 1989; 18: 1747–1766.

13.

Gaba

Winkler

. Implications of errors in survey data: a Bayesian model. Manage Sci 1992; 38: 913–925.

14.

Evans

Guttman

Haitovsky

Bayesian analysis of binary data subject to misclassification. In: Berry

Chaloner

Geweke

(eds). Bayesian Statistics and Econometrics: essays in honor of Arnold Zeller, New York: Wiley, 1996, pp. 67–77.

15.

Gustafson

Saskin

. Case-control analysis with partial knowledge of exposure misclassification probabilities. Biometrics 2001; 57: 598–609.

16.

Rahardja

Young

. Credible sets for risk ratios in over-reported two-sample binomial data using the double-sampling scheme. Comput Stat Data Anal 2010; 54: 1281–1287.

17.

Rahardja

Young

. Likelihood-based confidence intervals for the risk ratio using double sampling with over-reported binary data. Comput Stat Data Anal 2011; 55: 813–823.

18.

Rahardja

Zhao

. Likelihood-based confidence intervals for the risk difference of two-sample binary data with a fallible classifier and a gold standard. Stat Methodol 2011; 8: 204–212.

19.

Tang

Qiu

Poon

. Comparison of disease prevalence in two populations in presence of misclassification. Biom J 2012; 54: 786–807.

20.

Zou

Donner

. Construction of confidence limits about effect measures: a general approach. Stat Med 2008; 27: 1693–1702.

21.

Newcombe

. Interval estimation for the difference between independent proportions: comparison of eleven methods. Stat Med 1998; 17: 873–890.

22.

Newcombe RG. MOVER-R confidence intervals for ratios and products of two independently estimated quantities. Stat Methods Med Res. Epub ahead of print 9 October 2013. DOI: 10.1177/0962280213502144.

23.

Wilson

. Probable inference, the law of succession, and statistical inference. J Am Stat Assoc 1927; 22: 209–212.

24.

Agresti

Caffo

. Simple and effective confidence intervals for proportions and differences of proportions result from adding two successes and two failures. Am Stat 2000; 54: 280–288.

25.

Newcombe

. Logit confidence intervals and the inverse sinh transformation. Am Stat 2001; 55: 200–202.

26.

Fagerland

Newcombe

. Confidence intervals for odds ratio and relative risk based on the inverse hyperbolic sine transformation. Stat Med 2013; 32: 2823–2836.

27.

Newcombe

. Measures of location for confidence intervals for proportions. Commun Stat Theory Methods 2011; 40: 1743–1767.

28.

Pepe

. Inference using surrogate outcome data and a validation sample. Biometrika 1992; 79: 355–365.

29.

Hochberg

. On the use of double sampling schemes in analyzing categorical data with misclassification error. J Am Stat Assoc 1977; 72: 4–21.

30.

Yiu

Poon

. Estimating the polychoric correlation from misclassified data. Br J Math Stat Psychol 2008; 61: 133–161.