Conceptequivalent weights
Equivalent Weights
A statistical concept connecting model-assisted estimation with design-based inference. If a model-assisted estimator can be written in the linear form of a weighted sample mean, the corresponding weights are the equivalent weights; when the model is correct, the weighted estimator and the model prediction are asymptotically equivalent.
Timeline (last 90 days)
Oct 15
The basic idea of equivalent weights is: if a model-assisted estimator can be written in the linear form of a weighted sample mean, then the corresponding weights are the equivalent weights; when the model is correct, the weighted estimator based on these weights is asymptotically equivalent to the model prediction results.
Unverified50%