Comparison of models for analyzing two-group, cross-sectional data with a Gaussian outcome subject to a detection limit

• Published in: Statistical methods in medical research Vol. 25; no. 6; pp. 2733 - 2749
• Main Authors: Wiegand, Ryan E, Rose, Charles E, Karon, John M
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.12.2016; Sage Publications Ltd
• Subjects: Anti-HIV Agents - therapeutic use; Bias; Biological markers; Biomarkers; Computer programs; Confidence intervals; Cross sections; Cross-Sectional Studies - methods; Data analysis; HIV; HIV Infections - drug therapy; HIV Infections - virology; HIV-1 - drug effects; HIV-1 - genetics; HIV-1 - isolation & purification; Human immunodeficiency virus; Humans; Likelihood Functions; Limit of Detection; Multivariate Analysis; Normal Distribution; Probability; Raltegravir Potassium - therapeutic use; Regression analysis; RNA, Viral - analysis; RNA, Viral - genetics; Simulation; Software; Statistical methods; Statistical power; Viral Load - drug effects; statistical power; limit of detection; regression
• ISSN: 0962-2802; 1477-0334; 1477-0334
• DOI: 10.1177/0962280214531684

A potential difficulty in the analysis of biomarker data occurs when data are subject to a detection limit. This detection limit is often defined as the point at which the true values cannot be measured reliably. Multiple, regression-type models designed to analyze such data exist. Studies have compared the bias among such models, but few have compared their statistical power. This simulation study provides a comparison of approaches for analyzing two-group, cross-sectional data with a Gaussian-distributed outcome by exploring statistical power and effect size confidence interval coverage of four models able to be implemented in standard software. We found using a Tobit model fit by maximum likelihood provides the best power and coverage. An example using human immunodeficiency virus type 1 ribonucleic acid data is used to illustrate the inferential differences in these models.