Risk difference tests for stratified binary data under Dallal’s model
Authors:
- 27 June 2022
- journal article
- research article
- Published by SAGE Publications in Statistical Methods in Medical Research
- Vol. 31 (6) , 1135-1156
Abstract
In medical studies, the binary data is often encountered when the paired organs or body parts receive treatment. However, the same treatment may lead to different therapeutic effects based on the stratified factors or confounding effects. Under Dallal’s model, the paper proposes the homogeneity test of risk difference to determine the necessity of stratified treatment. When the stratification is not necessary, common test is introduced to investigate if the risk difference is equal to a fixed constant between two groups. Several statistical tests are derived to analyze homogeneity and common hypotheses, respectively. Monte Carlo simulations show that the score tests behave well in both of hypotheses. Wald-type and Rosner’s statistics are always liberal but have higher empirical powers. Especially, the likelihood ratio statistic is better for the homogeneity test in the case of smaller data with larger strata. Two real examples are provided to illustrate the effectiveness of the proposed methods in ankle instability and otolaryngology studies.Keywords
This publication has 25 references indexed in Scilit:
- Objective Bayesian Inference for Bilateral DataBayesian Analysis, 2015
- Testing homogeneity of proportion ratios for stratified correlated bilateral data in two‐arm randomized clinical trialsStatistics in Medicine, 2014
- Homogeneity test, sample size determination and interval construction of difference of two proportions in stratified bilateral-sample designsJournal of Statistical Planning and Inference, 2012
- Testing Equality of Correlations of Two Paired Binary Responses from Two Treated Groups in a Randomized TrialJournal of Biopharmaceutical Statistics, 2011
- Sample Size for Testing Difference Between Two Proportions for the Bilateral-Sample DesignJournal of Biopharmaceutical Statistics, 2009
- Testing the equality of proportions for correlated otolaryngologic dataComputational Statistics & Data Analysis, 2008
- Likelihood Ratio, Score, and Wald Tests in a Constrained Parameter SpaceThe American Statistician, 2007
- The chi 2 test for data collected on eyes.British Journal of Ophthalmology, 1993
- Paired Bernoulli TrialsBiometrics, 1988
- Duration of effusion after antibiotic treatment for acute otitis mediaThe Pediatric Infectious Disease Journal, 1982