Year: 2025
Type: article
Abstract: PURPOSE To evaluate the performance of various analysis approaches for skewed correlated eye data from two eyes of a subject in the same comparison group, which is common in ophthalmology and vision research. Design Simulation study and real-world data analysis. Subjects Simulated subjects and participants of Dry Eye Assessment and Management (DREAM) Study METHODS We simulated skewed correlated data using (skewness, kurtosis)=(27,50) and (0.06, 5.9), inter-eye correlation (ρ=0, 0.25, 0.50, 0.75), sample sizes (n=20, 50, 100, 200), mean differences between two groups (0 for type 1 error rate, 0.2 for statistical power). Each simulated dataset was analyzed without and with applying rank-based normalization: (1) two-sample t-test of two eye data; (2) two-sample t-test of random eye data; (3) Wald test from generalized estimating equations (GEE-Wald); (4) GEE score test (GEE-score); (5) F-test from linear mixed-effects model (LMM); (6) clustered Wilcoxon test of Rosner, Glynn and Lee; (7) clustered Wilcoxon test of Datta and Satten; (8) Wilcoxon rank sum test of two eyes ignoring inter-eye correlation; (9) Wilcoxon rank sum test on average of two eyes. We demonstrated analysis of skewed tear break-up time (TBUT) data from the DREAM Study. Main Outcome Measures Type 1 error rate and statistical power. RESULTS T-test and Wilcoxon test on two eye data without accounting for inter-eye correlation inflated type 1 error rate up to 0.13, and GEE-Wald inflated type 1 error rate to 0.08 when sample size is small, while all other tests maintained type 1 error rate close to 0.05. For skewed data without normalization, t-test of random eye, GEE-Wald, GEE-score, and LMM had substantially lower power than clustered Wilcoxon methods. After normalization, GEE-score and LMM achieved similar or slightly higher power than clustered Wilcoxon methods. Results from analysis of TBUT are consistent with simulation findings. CONCLUSION When comparing skewed correlated eye measures between two groups of subjects with their two eyes in the same comparison group, clustered Wilcoxon methods can be used. Alternatively, skewed data can be normalized before applying GEE-score or LMM, which may achieve slightly higher statistical power than clustered Wilcoxon methods and offers flexibility to adjust for other covariates.
Source: Ophthalmology Science
Authors: Sifan Zhang, Ziyi You, Bernard Rosner, Gui-shuang Ying
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,500
OpenAlex ID: W4416684059