Prediction-Powered Inference with Inverse Probability Weighting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Datta, Jyotishka, Polson, Nicholas G.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915884867518464
author Datta, Jyotishka
Polson, Nicholas G.
author_facet Datta, Jyotishka
Polson, Nicholas G.
contents Prediction-powered inference (PPI) is a recent framework for valid statistical inference with partially labeled data, combining model-based predictions on a large unlabeled set with bias correction from a smaller labeled subset. Building on existing PPI results under covariate shift, we show that PPI rectification admits a direct design-based interpretation, and that informative labeling can be handled naturally by Horvitz--Thompson and Hájek-style corrections. This connection unites design-based survey sampling ideas with modern prediction-assisted inference, yielding estimators that remain valid when labeling probabilities vary across units. We consider the common setting where the inclusion probabilities are not known but estimated from a correctly specified model. In simulations, the performance of IPW-adjusted PPI with estimated propensities closely matches the known-probability case, retaining both nominal coverage and the variance-reduction benefits of PPI.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10149
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prediction-Powered Inference with Inverse Probability Weighting
Datta, Jyotishka
Polson, Nicholas G.
Machine Learning
62D10, 62F10, 62-02
Prediction-powered inference (PPI) is a recent framework for valid statistical inference with partially labeled data, combining model-based predictions on a large unlabeled set with bias correction from a smaller labeled subset. Building on existing PPI results under covariate shift, we show that PPI rectification admits a direct design-based interpretation, and that informative labeling can be handled naturally by Horvitz--Thompson and Hájek-style corrections. This connection unites design-based survey sampling ideas with modern prediction-assisted inference, yielding estimators that remain valid when labeling probabilities vary across units. We consider the common setting where the inclusion probabilities are not known but estimated from a correctly specified model. In simulations, the performance of IPW-adjusted PPI with estimated propensities closely matches the known-probability case, retaining both nominal coverage and the variance-reduction benefits of PPI.
title Prediction-Powered Inference with Inverse Probability Weighting
topic Machine Learning
62D10, 62F10, 62-02
url https://arxiv.org/abs/2508.10149