Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 4;41(2):btaf055.
doi: 10.1093/bioinformatics/btaf055.

ipd: an R package for conducting inference on predicted data

Stephen Salerno  1 , Jiacheng Miao  2 , Awan Afiaz  1   3 , Kentaro Hoffman  4 , Anna Neufeld  5 , Qiongshi Lu  2 , Tyler H McCormick  4   6 , Jeffrey T Leek  1   3
Affiliations

ipd: an R package for conducting inference on predicted data

Stephen Salerno et al. Bioinformatics. .

Abstract

Summary: ipd is an open-source R software package for the downstream modeling of an outcome and its associated features where a potentially sizable portion of the outcome data has been imputed by an artificial intelligence or machine learning prediction algorithm. The package implements several recent proposed methods for inference on predicted data with a single, user-friendly wrapper function, ipd. The package also provides custom print, summary, tidy, glance, and augment methods to facilitate easy model inspection. This document introduces the ipd software package and provides a demonstration of its basic usage.

Availability: ipd is freely available on CRAN or as a developer version at our GitHub page: github.com/ipd-tools/ipd. Full documentation, including detailed instructions and a usage 'vignette' are available at github.com/ipd-tools/ipd.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
Point estimate and corresponding 95% confidence intervals for four available IPD methods (postpi, ppi, ppi_plusplus, and pspa; second row), as compared to three benchmark regressions (oracle, naive, and classical; first row) on 1000 simulated linear regression datasets.
See this image and copyright information in PMC

References

    1. Angelopoulos AN, Bates S, Fannjiang C et al. Prediction-powered inference. Science 2023a;382:669–74. - PubMed
    1. Angelopoulos AN, Duchi JC, Zrnic T. PPI++: Efficient prediction-powered inference. arXiv, arXiv:2311.01453, 2023b, preprint: not peer reviewed.
    1. Egami N, Hinck M, Stewart B et al. Using imperfect surrogates for downstream inference: design-based supervised learning for social science applications of large language models. Adv Neural Inf Process Syst 2023;36:68589–601.
    1. Hoffman K, Salerno S, Afiaz A et al. Do we really even need data? arXiv, arXiv:2401.08702, 2024, preprint: not peer reviewed.
    1. Miao J, Lu Q. Task-agnostic machine learning-assisted inference. Adv Neural Inf Process Syst 2024;37:106162–89.