mn.ipw: Inverse probability weighted estimation of population means

In RCAL: Regularized Calibrated Estimation

Description

This function implements inverse probability weighted (IPW) estimation of population means with missing data, provided fitted propensity scores.

Usage

mn.ipw(y, tr, fp)

Arguments

y	An n x 1 vector of outcomes with missing data.
tr	An n x 1 vector of non-missing indicators (=1 if y is observed or 0 if y is missing).
fp	An n x 1 vector of fitted propensity scores.

Details

The ratio IPW estimate is the direct IPW estimate divided by that with y replaced by a vector of 1s. The latter is referred to as the direct IPW estimate of 1.

Value

one	The direct IPW estimate of 1.
est	The ratio IPW estimate.

References

Tan, Z. (2020a) Regularized calibrated estimation of propensity scores with model misspecification and high-dimensional data, Biometrika, 107, 137<e2><80><93>158.

Tan, Z. (2020b) Model-assisted inference for treatment effects using regularized calibrated estimation with high-dimensional data, Annals of Statistics, 48, 811<e2><80><93>837.

RCAL documentation built on Nov. 8, 2020, 4:22 p.m.