Inverse probability weighting is used to address which issue in cohort studies?

• A. It handles confounding at baseline
• B. It imputes missing data
• C. It adjusts standard errors for clustering
• D. It addresses selection bias from loss to follow-up and missing data

Answer: (D)

Inverse probability weighting addresses selection bias that arises when some participants are lost to follow-up or have missing data. The idea is to reweight the observed individuals by the inverse of their probability of remaining in the study (given their covariates). Those who were less likely to be observed get larger weights, helping the weighted sample resemble the full original cohort. This helps correct for informative censoring, where dropout or missingness is related to exposure or outcome, which would otherwise bias the exposure–outcome association.

While weighting can be used to tackle confounding when applied to the probability of receiving a treatment or exposure, the context here centers on bias from loss to follow-up and missing data. Imputing missing data is a different approach (not inverse probability weighting), and adjusting standard errors for clustering is handled by other methods.