Common risk difference test and interval estimation of risk difference for stratified bilateral correlated data

Abstract

Bilateral correlated data are often encountered in medical researches such as ophthalmologic (or otolaryngologic) studies, in which each unit contributes information from paired organs to the data analysis, and the measurements from such paired organs are generally highly correlated. Various statistical methods have been developed to tackle intra-class correlation on bilateral correlated data analysis. In practice, it is very important to adjust the effect of confounder on statistical inferences, since either ignoring the intra-class correlation or confounding effect may lead to biased results. In this article, we propose three approaches for testing common risk difference for stratified bilateral correlated data under the assumption of equal correlation. Five confidence intervals of common difference of two proportions are derived. The performance of the proposed test methods and confidence interval estimations is evaluated by Monte Carlo simulations. The simulation results show that the score test statistic outperforms other statistics in the sense that the former has robust type [Formula: see text] error rates with high powers. The score confidence interval induced from the score test statistic performs satisfactorily in terms of coverage probabilities with reasonable interval widths. A real data set from an otolaryngologic study is used to illustrate the proposed methodologies.

Risk difference tests for stratified binary data under Dallal’s model

“…Under the common test H 02 , Rosner's statistic is equivalent to the Wald-type test T c W . We can prove this conclusion through the result of Wald-type test in Shen et al 17 .…”

“…For the stratified design, Shen et al 16 considered the homogeneity of risk difference in two proportions. The common test of risk difference has been investigated by Shen et al 17 . More detailed topics under Donner's model are referred to Pei et al 18 and Zhuang et al 19 We are motivated by two real examples of ankle instability and otolaryngology.…”

Statistical methods for the bilateral correlated data

“…然 而, 具有约束的最大似然估计是建立在所有分层的共同差异等于 0 的基础上的. Shen 等 [36] 提出了 3 种方法 (似然比检验、Wald 检验和得分检验) 检验在相关系数相等的条件下分层双边数据的共同风险 差异. 此外, 他们得到了两个比值共同差异的 5 个置信区间, 其中包括两个权重修正方法 (全局 Wald 置信区间和替代 Wald 置信区间) 和 3 个基于测试的方法 (似然置信区间、完全 Wald 置信区间和得 分置信区间).…”

Testing the common risk difference of proportions for stratified uni‐ and bilateral correlated data

“…Under Donner's model, Pei, Tian, and Tang (2014) developed five statistics for testing the homogeneity of proportion ratios. Shen and Ma (2017, 2019) derived some procedures from testing homogeneity and common risk difference of two proportions. Zhuang, Tian, and Ma (2019a, 2019b) considered the homogeneity test and CI for proportion ratios.…”