Estimate Level Adjustment For Inference With Proxies Under Random Distribution Shifts

ArXi:2605.06484v1 Announce Type: cross In many scientific domains, including experimentation, researchers rely on measurements of proxy outcomes to achieve faster and frequent reads, especially when the primary outcome of interest is challenging to measure directly. While proxies offer a readily accessible observation for inference, the ultimate goal is to draw statistical inferences about the primary outcome parameter and proxy data are typically imperfect in some ways.