Homogeneity Tests and Interval Estimations of Risk Differences for Stratified Bilateral and Unilateral Correlated Data


Chang-Xing Ma, Shuyi Liang

Introduction


Homogeneity tests and interval estimations of the risk difference between two groups are of general interest under paired Bernoulli settings with the presence of stratification effects. Dallal [1] proposed a model by parameterizing the probability of an occurrence at one site given an occurrence at the other site. Based on this model, we propose three test statistics and evaluate their performances regarding type I error controls and powers. Confidence intervals of a common risk difference with satisfactory coverage probabilities and interval length are constructed. Our simulation results show that the score test is the most robust and the profile likelihood confidence interval outperforms other methods proposed. Data from a study of acute otitis media is used to illustrate our proposed procedures.

References
1. Testing homogeneity of difference of two proportions for stratified correlated paired binary data
2. Homogeneity Tests and Interval Estimations of Risk Differences for Stratified Bilateral and Unilateral Correlated Data


Calculator


■ DATA


Data format:
Strata
1 2 ... J
Response Group1 Group2 Group1 Group2 … … Group1 Group2
Unilateral 0 m110 m120 m202 m202 … … mJ02 mJ02
1 m111 m121 m211 m212 … … mJ11 mJ12
Bilateral 0 n110 n120 n201 n202 … … nJ01 nJ02
1 n111 n121 n211 n212 … … nJ11 nJ12
2 n112 n122 n221 n222 … … nJ21 nJ22

Please put your data in the box below,
or try the example in the paper,
or simulate data - turn simulation panel On Off
5 × (2 J)   matrix separated by space or comma (J - number of strata)

■ OPTIONS


Test common risk difference d0: Default: 0
Significant level α: Default: 0.05, Confidence level = (1-α)*100

■