search

jaspershen-lab / ipop_aging

Code for aging project
MIT License
22 stars 9 forks source link

Question about data adjustment #2

Open Selina-f opened 3 weeks ago

Selina-f commented 3 weeks ago

You utilized the intensity of each feature as the dependent variable (Y), while treating the confounding factors (BMI, sex, IRIS, and ethnicity) as independent variables (X) to construct a linear regression model. Why is the residual of the model used as the adjusted value for the specific feature instead of the predicted value? Thanks for your answer!

jaspershen commented 3 weeks ago

Thank you. The method we used is from this paper: https://link-springer-com.stanford.idm.oclc.org/article/10.1007/s11306-016-1050-5. This is a common method for confounder adjustment in omics study. Thank you!