Login / Signup

Comparison of methods for handling covariate missingness in propensity score estimation with a binary exposure.

Donna L CoffmanJiangxiu ZhouXizhen Cai
Published in: BMC medical research methodology (2020)
Applying GBM to the incomplete data and relying on the surrogate split approach resulted in substantial bias. Imputation prior to implementing GBM is recommended.
Keyphrases
  • electronic health record
  • big data
  • quality improvement
  • ionic liquid
  • clinical evaluation