{"url":"/dataset/ihdp","name":"IHDP","full_name":"Infant Health and Development Program","description_markdown":"The Infant Health and Development Program (IHDP) is a randomized controlled study designed to evaluate the effect of home visit from specialist doctors on the cognitive test scores of premature infants. The datasets is first used for benchmarking treatment effect estimation algorithms in Hill [35], where selection bias is induced by removing non-random subsets of the treated individuals to create an observational dataset, and the outcomes are generated using the original covariates and treatments. It contains 747 subjects and 25 variables.","description_withheld":null,"homepage":"https://causalforge.readthedocs.io/en/latest/user_guide/Loading_Causal_RW_Benchmarking_Datasets.html","introduced_date":"2016-06-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/estimating-individual-treatment-effect","title":"Estimating individual treatment effect: generalization bounds and algorithms","first_author":"Uri Shalit","url":null},"license":null,"modalities":[],"tasks":[{"name":"Causal Inference","url":"/task/causal-inference","datasets_with_task":"/datasets/task/causal-inference"},{"name":"Heterogeneous Treatment Effect Estimation","url":"/task/heterogeneous-treatment-effect-estimation","datasets_with_task":"/datasets/task/heterogeneous-treatment-effect-estimation"}],"languages":[],"variants":["IHDP"],"data_loaders":[],"num_papers_in_archive":189,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/causal-inference-on-ihdp","task":"Causal Inference","dataset_variant":"IHDP","rows":13,"metrics":["Average Treatment Effect Error"],"first_row_in_archive_order":{"model":"SIP + BCAUSS","paper":"/paper/preventing-spurious-interactions-a-new","metrics":{"Average Treatment Effect Error":"0.13"},"code_links":[{"title":"RogerG2/NNSIP","url":"https://github.com/RogerG2/NNSIP"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/heterogeneous-treatment-effect-estimation-on","task":"Heterogeneous Treatment Effect Estimation","dataset_variant":"IHDP","rows":2,"metrics":["PEHE"],"first_row_in_archive_order":{"model":"CausalPFN","paper":"/paper/causalpfn-amortized-causal-effect-estimation","metrics":{"PEHE":"0.58"},"code_links":[{"title":"vdblm/CausalPFN","url":"https://github.com/vdblm/CausalPFN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/causalpfn-amortized-causal-effect-estimation","title":"CausalPFN: Amortized Causal Effect Estimation via In-Context Learning","date":"2025-06-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/preventing-spurious-interactions-a-new","title":"Preventing Spurious Interactions: A New Inductive Bias for Accurate Treatment Effect Estimation","date":"2025-05-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/learning-end-to-end-patient-representations","title":"Learning end-to-end patient representations through self-supervised covariate balancing for causal treatment effect estimation","date":"2023-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/minimizing-bias-in-massive-multi-arm","title":"Minimizing bias in massive multi-arm observational studies with BCAUS: balancing covariates automatically using supervision","date":"2021-09-20","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-representation-learning-for","title":"Deep representation learning for individualized treatment effect estimation using electronic health records","date":"2019-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adapting-neural-networks-for-the-estimation","title":"Adapting Neural Networks for the Estimation of Treatment Effects","date":"2019-06-05","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/causal-effect-inference-with-deep-latent","title":"Causal Effect Inference with Deep Latent-Variable Models","date":"2017-05-24","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/estimating-individual-treatment-effect","title":"Estimating individual treatment effect: generalization bounds and algorithms","date":"2016-06-13","rows_on_this_dataset":8,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}