Common Test and Interval Estimation of Risk Ratio for Complex Paired Data Under Dallal’s Model

Unilateral or bilateral paired data are often encountered when people receive treatment for paired organs or body parts. Compared with using only unilateral or bilateral data alone, the utilization of combined data can provide additional information. With combined unilateral and bilateral data, this article aims to propose three statistical tests and three confidence interval methods of relative risk ratio in a stratified design under Dallal’s model. Our simulation results show that the score test has a more robust type I error rate compared to other tests in all cases. Meanwhile, the confidence interval method based on the score test always provides coverage probability close to the nominal level and satisfactory coverage width. Finally, two real examples of otolaryngology and myopathy are applied to illustrate the application of the proposed tests and confidence interval methods.