Quantile Regression in the Secondary Analysis of Case-Control Data

Area of Science:

• Epidemiology
• Biostatistics
• Statistical Genetics

Background:

• Case-control studies are common for disease-factor association research.
• Existing methods for secondary continuous outcomes often focus solely on the mean.
• There's a need for comprehensive analysis of covariates' effects on various parts of the outcome distribution.

Purpose of the Study:

• To propose a novel quantile-based statistical approach for analyzing continuous secondary outcomes in case-control studies.
• To enable a thorough investigation of how covariates influence multiple quantiles of a secondary outcome.
• To provide a cost-effective method for utilizing existing case-control data for secondary outcome research.

Main Methods:

• Development of a new family of estimating equations.
• Combining observed and pseudo outcomes for consistent conditional quantile estimation.
• Utilizing case-control data for robust statistical inference.

Main Results:

• The proposed quantile-based approach allows for consistent estimation of conditional quantiles.
• Simulations demonstrate the effectiveness and performance of the new method.
• The approach was successfully applied to a real-world case-control study on asthma genetics.

Conclusions:

• The proposed quantile-based method offers a powerful and comprehensive tool for analyzing continuous secondary outcomes in case-control studies.
• This approach extends the utility of case-control data beyond mean-based analyses.
• The method provides valuable insights into covariate effects across the entire outcome distribution.