Adjusted inference procedures for the interobserver agreement in twin studies

Stephanie N Dixon; Allan Donner; Mohamed M Shoukri

doi:10.1177/0962280213476771

Adjusted inference procedures for the interobserver agreement in twin studies

Stat Methods Med Res. 2016 Aug;25(4):1260-71. doi: 10.1177/0962280213476771. Epub 2013 Mar 12.

Authors

Stephanie N Dixon¹, Allan Donner², Mohamed M Shoukri³

Affiliations

¹ Department of Epidemiology and Biostatistics, Western University, London, ON, Canada Division of Nephrology, Department of Medicine, London Health Science Centre and Western University, London, ON, Canada [email protected].
² Department of Epidemiology and Biostatistics, Western University, London, ON, Canada.
³ Department of Epidemiology and Biostatistics, Western University, London, ON, Canada Department of Scientific Computing, King Faisal Specialist Hospital and Research Centre, Riyadh, Kingdom of Saudi Arabia.

PMID: 23487017
DOI: 10.1177/0962280213476771

Abstract

We propose adjusted inference procedures for evaluating the agreement/disagreement of two raters in a clustered setting involving twins or paired body parts. These procedures include the construction of a confidence interval for the kappa statistic, a related test of statistical significance and a formula that facilitates sample size estimation. The results of a simulation study suggest that a simple adjustment using an estimated design effect will provide valid inferences. The methods proposed are illustrated using an example from the literature.

Keywords: Paired data; confidence interval construction; goodness-of-fit significance test; kappa statistic; sample size estimation.

MeSH terms

Confidence Intervals*
Female
Humans
Mammography / methods*
Models, Statistical
Observer Variation*
Reproducibility of Results
Research Design
Sample Size
Twin Studies as Topic / methods*