Objective: This paper aims to compare the performance of regression-based statistical approaches that were currently used or advocated to adjust a treatment effect. Methods: The six methods used to compare their relative performance were: excluding treated individuals from data, no adjustment for treatment effect, modelling treatment as a covariate(indicator variable), non-parametric adjustment of treatment, adding a constant value to measurements for treated individuals, and censored normal regression. We applied these methods to real genetic and clinical data from Yonsei cardiovascular genome center to demonstrate a pattern of their behaviour. Results: Two of the adjustment methods were more powerful than other methods for analysis of genetic association with serum lipid profiles. These were: no adjustment to the observed lipid profiles in treated subjects, non-parametric adjustment method based on averaging ordered residuals. Conclusion: Non-parametric adjustment method based on averaging ordered residuals and no adjustment to the observed lipid profiles in treated subjects can effectively adjust the distorting effect of lipid-lowering drug and recover a marked loss in statistical power. Also, in genetic association studies of continuous traits that distortion arising from a treatment effect really matters, we proposed to use the appropriate methods that are more effective and straightforward to implement