Methodology session 5: Appropriate analysis in Add Health—Correcting for design effects and selecting weights

Citation

Chen, Ping (2018). Methodology session 5: Appropriate analysis in Add Health—Correcting for design effects and selecting weights. 2018 Add Health Users Conference. Bethesda, MD.

Abstract

Add Health is a national longitudinal study with special survey design features. This session will discuss how users can account for those features, including clustering, stratification, and unequal probability of selection. It will focus on how to choose correct sampling weights and avoid common errors. It will also give specific examples of how to apply weights to run descriptive statistics, population-average models, subpopulation analysis, and multilevel models.

URL

https://addhealth.cpc.unc.edu/wp-content/uploads/docs/user_guides/Appropriate_Analysis_in_Add_Health_Correcting_for_Design_Effects_and_Selecting_Weights_Chen.pdf

Reference Type

Conference proceeding

Book Title

2018 Add Health Users Conference

Author(s)

Chen, Ping

Year Published

2018

City of Publication

Bethesda, MD

Reference ID

6268