Metalearners for estimating heterogeneous treatment effects using machine learning

There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the condition...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the National Academy of Sciences - PNAS Vol. 116; no. 10; pp. 4156 - 4165
Main Authors Künzel, Sören R., Sekhon, Jasjeet S., Bickel, Peter J., Yu, Bin
Format Journal Article
LanguageEnglish
Published United States National Academy of Sciences 05.03.2019
SeriesPNAS Plus
Subjects
Online AccessGet full text
ISSN0027-8424
1091-6490
1091-6490
DOI10.1073/pnas.1804597116

Cover

Abstract There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the conditional average treatment effect (CATE) function. Metaalgorithms build on base algorithms—such as random forests (RFs), Bayesian additive regression trees (BARTs), or neural networks—to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a metaalgorithm, the X-learner, that is provably efficient when the number of units in one treatment group is much larger than in the other and can exploit structural properties of the CATE function. For example, if the CATE function is linear and the response functions in treatment and control are Lipschitz-continuous, the X-learner can still achieve the parametric rate under regularity conditions. We then introduce versions of the X-learner that use RF and BART as base learners. In extensive simulation studies, the X-learner performs favorably, although none of the metalearners is uniformly the best. In two persuasion field experiments from political science, we demonstrate how our X-learner can be used to target treatment regimes and to shed light on underlying mechanisms. A software package is provided that implements our methods.
AbstractList There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the conditional average treatment effect (CATE) function. Metaalgorithms build on base algorithms—such as random forests (RFs), Bayesian additive regression trees (BARTs), or neural networks—to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a metaalgorithm, the X-learner, that is provably efficient when the number of units in one treatment group is much larger than in the other and can exploit structural properties of the CATE function. For example, if the CATE function is linear and the response functions in treatment and control are Lipschitz-continuous, the X-learner can still achieve the parametric rate under regularity conditions. We then introduce versions of the X-learner that use RF and BART as base learners. In extensive simulation studies, the X-learner performs favorably, although none of the metalearners is uniformly the best. In two persuasion field experiments from political science, we demonstrate how our X-learner can be used to target treatment regimes and to shed light on underlying mechanisms. A software package is provided that implements our methods.
There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the conditional average treatment effect (CATE) function. Metaalgorithms build on base algorithms-such as random forests (RFs), Bayesian additive regression trees (BARTs), or neural networks-to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a metaalgorithm, the X-learner, that is provably efficient when the number of units in one treatment group is much larger than in the other and can exploit structural properties of the CATE function. For example, if the CATE function is linear and the response functions in treatment and control are Lipschitz-continuous, the X-learner can still achieve the parametric rate under regularity conditions. We then introduce versions of the X-learner that use RF and BART as base learners. In extensive simulation studies, the X-learner performs favorably, although none of the metalearners is uniformly the best. In two persuasion field experiments from political science, we demonstrate how our X-learner can be used to target treatment regimes and to shed light on underlying mechanisms. A software package is provided that implements our methods.There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the conditional average treatment effect (CATE) function. Metaalgorithms build on base algorithms-such as random forests (RFs), Bayesian additive regression trees (BARTs), or neural networks-to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a metaalgorithm, the X-learner, that is provably efficient when the number of units in one treatment group is much larger than in the other and can exploit structural properties of the CATE function. For example, if the CATE function is linear and the response functions in treatment and control are Lipschitz-continuous, the X-learner can still achieve the parametric rate under regularity conditions. We then introduce versions of the X-learner that use RF and BART as base learners. In extensive simulation studies, the X-learner performs favorably, although none of the metalearners is uniformly the best. In two persuasion field experiments from political science, we demonstrate how our X-learner can be used to target treatment regimes and to shed light on underlying mechanisms. A software package is provided that implements our methods.
Estimating and analyzing heterogeneous treatment effects is timely, yet challenging. We introduce a unifying framework for many conditional average treatment effect estimators, and we propose a metalearner, the X-learner, which can adapt to structural properties, such as the smoothness and sparsity of the underlying treatment effect. We present its favorable properties, using theory and simulations. We apply it, using random forests, to two field experiments in political science, where it is shown to be easy to use and to produce results that are interpretable. There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the conditional average treatment effect (CATE) function. Metaalgorithms build on base algorithms—such as random forests (RFs), Bayesian additive regression trees (BARTs), or neural networks—to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a metaalgorithm, the X-learner, that is provably efficient when the number of units in one treatment group is much larger than in the other and can exploit structural properties of the CATE function. For example, if the CATE function is linear and the response functions in treatment and control are Lipschitz-continuous, the X-learner can still achieve the parametric rate under regularity conditions. We then introduce versions of the X-learner that use RF and BART as base learners. In extensive simulation studies, the X-learner performs favorably, although none of the metalearners is uniformly the best. In two persuasion field experiments from political science, we demonstrate how our X-learner can be used to target treatment regimes and to shed light on underlying mechanisms. A software package is provided that implements our methods.
Estimating and analyzing heterogeneous treatment effects is timely, yet challenging. We introduce a unifying framework for many conditional average treatment effect estimators, and we propose a metalearner, the X-learner, which can adapt to structural properties, such as the smoothness and sparsity of the underlying treatment effect. We present its favorable properties, using theory and simulations. We apply it, using random forests, to two field experiments in political science, where it is shown to be easy to use and to produce results that are interpretable. There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the conditional average treatment effect (CATE) function. Metaalgorithms build on base algorithms—such as random forests (RFs), Bayesian additive regression trees (BARTs), or neural networks—to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a metaalgorithm, the X-learner, that is provably efficient when the number of units in one treatment group is much larger than in the other and can exploit structural properties of the CATE function. For example, if the CATE function is linear and the response functions in treatment and control are Lipschitz-continuous, the X-learner can still achieve the parametric rate under regularity conditions. We then introduce versions of the X-learner that use RF and BART as base learners. In extensive simulation studies, the X-learner performs favorably, although none of the metalearners is uniformly the best. In two persuasion field experiments from political science, we demonstrate how our X-learner can be used to target treatment regimes and to shed light on underlying mechanisms. A software package is provided that implements our methods.
SignificanceEstimating and analyzing heterogeneous treatment effects is timely, yet challenging. We introduce a unifying framework for many conditional average treatment effect estimators, and we propose a metalearner, the X-learner, which can adapt to structural properties, such as the smoothness and sparsity of the underlying treatment effect. We present its favorable properties, using theory and simulations. We apply it, using random forests, to two field experiments in political science, where it is shown to be easy to use and to produce results that are interpretable. There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of metaalgorithms that can take advantage of any supervised learning or regression method in machine learning and statistics to estimate the conditional average treatment effect (CATE) function. Metaalgorithms build on base algorithms—such as random forests (RFs), Bayesian additive regression trees (BARTs), or neural networks—to estimate the CATE, a function that the base algorithms are not designed to estimate directly. We introduce a metaalgorithm, the X-learner, that is provably efficient when the number of units in one treatment group is much larger than in the other and can exploit structural properties of the CATE function. For example, if the CATE function is linear and the response functions in treatment and control are Lipschitz-continuous, the X-learner can still achieve the parametric rate under regularity conditions. We then introduce versions of the X-learner that use RF and BART as base learners. In extensive simulation studies, the X-learner performs favorably, although none of the metalearners is uniformly the best. In two persuasion field experiments from political science, we demonstrate how our X-learner can be used to target treatment regimes and to shed light on underlying mechanisms. A software package is provided that implements our methods.
Author Bickel, Peter J.
Künzel, Sören R.
Yu, Bin
Sekhon, Jasjeet S.
Author_xml – sequence: 1
  givenname: Sören R.
  surname: Künzel
  fullname: Künzel, Sören R.
– sequence: 2
  givenname: Jasjeet S.
  surname: Sekhon
  fullname: Sekhon, Jasjeet S.
– sequence: 3
  givenname: Peter J.
  surname: Bickel
  fullname: Bickel, Peter J.
– sequence: 4
  givenname: Bin
  surname: Yu
  fullname: Yu, Bin
BackLink https://www.ncbi.nlm.nih.gov/pubmed/30770453$$D View this record in MEDLINE/PubMed
https://www.osti.gov/servlets/purl/1604674$$D View this record in Osti.gov
BookMark eNqFkU1v1DAURS1URKeFNStQBBsklPY5sWN7g4QqPioVISFYWx7Py0xGiT3YTqv-e5xmaKGLdhXJPu_mvuMjcuC8Q0JeUjihIOrTnTPxhEpgXAlKmydkQUHRsmEKDsgCoBKlZBU7JEcxbgFAcQnPyGENQuSZekF-fMNkejTBYYhF60OBMXWDSZ1bFxtMGPwaHfoxFimgSQO6VGDbok2xGONEDcZuOofFTUo-eE6etqaP-GL_PSa_Pn_6efa1vPj-5fzs40VpuahSuVoq00rTWoFUUIZKUmmBGgAuOFtCk1eSfKXAGGWXggNH2lYcjFBUtLWpjwnMuaPbmesr0_d6F3L1cK0p6EmPnvToOz155MM8shuXA65sXiaYuzFvOv3_jes2eu0vdcMoyJrmgDdzgM-WdLRdQrux3rnsQ9MGWCNYht7t_xL87zH71EMXLfa9uRGpqwpAZBCmvLf30K0fg8vadEUVoxWoZqJe_1v7tu_fZ8wAnwEbfIwBW52b5Tf00xZd_4CP03tzjxt8v68yXTxOv5rpbUw-3OJV08jcXdZ_APAt2J0
CitedBy_id crossref_primary_10_3390_app10072216
crossref_primary_10_1002_sim_10333
crossref_primary_10_1515_jci_2024_0009
crossref_primary_10_1214_20_AOAS1322
crossref_primary_10_3389_fmed_2022_864882
crossref_primary_10_1007_s10109_023_00413_0
crossref_primary_10_1007_s10994_021_05969_w
crossref_primary_10_1016_j_datak_2025_102416
crossref_primary_10_1016_j_softx_2022_101294
crossref_primary_10_1145_3629169
crossref_primary_10_1016_j_ejor_2022_01_046
crossref_primary_10_1109_ACCESS_2023_3260184
crossref_primary_10_1214_24_EJS2332
crossref_primary_10_1007_s11129_023_09278_5
crossref_primary_10_1214_23_EJS2157
crossref_primary_10_1007_s13218_024_00883_4
crossref_primary_10_1016_j_ssresearch_2022_102810
crossref_primary_10_2139_ssrn_3974859
crossref_primary_10_1093_biomet_asab042
crossref_primary_10_1093_biomtc_ujaf019
crossref_primary_10_1093_jrsssb_qkad075
crossref_primary_10_2139_ssrn_3676759
crossref_primary_10_2147_CLEP_S274466
crossref_primary_10_1016_j_jclinepi_2019_12_012
crossref_primary_10_1080_07350015_2020_1847122
crossref_primary_10_1287_isre_2022_1149
crossref_primary_10_1177_0272989X211064604
crossref_primary_10_1016_j_apenergy_2024_124550
crossref_primary_10_1097_EDE_0000000000001785
crossref_primary_10_1161_JAHA_124_034862
crossref_primary_10_1002_cai2_119
crossref_primary_10_1186_s12874_024_02202_9
crossref_primary_10_1002_sim_9955
crossref_primary_10_1109_TNNLS_2021_3133337
crossref_primary_10_1007_s10549_023_07237_y
crossref_primary_10_1016_j_neucom_2024_127741
crossref_primary_10_1038_s41598_022_16260_w
crossref_primary_10_1186_s12874_023_01889_6
crossref_primary_10_1016_j_jval_2022_07_011
crossref_primary_10_1371_journal_pone_0306711
crossref_primary_10_1016_j_jbi_2022_104256
crossref_primary_10_1080_19466315_2020_1819404
crossref_primary_10_1214_19_STS721
crossref_primary_10_1177_09622802231224628
crossref_primary_10_1016_j_jclinepi_2024_111538
crossref_primary_10_1146_annurev_publhealth_040119_094437
crossref_primary_10_21105_joss_05587
crossref_primary_10_1016_j_diabres_2022_110047
crossref_primary_10_1016_j_jlamp_2024_101000
crossref_primary_10_1513_AnnalsATS_202211_946OC
crossref_primary_10_3390_math12203301
crossref_primary_10_1111_dom_15744
crossref_primary_10_1080_07350015_2025_2479646
crossref_primary_10_1016_S2213_2600_24_00405_3
crossref_primary_10_3390_app14219700
crossref_primary_10_1111_ajps_12723
crossref_primary_10_1145_3643139
crossref_primary_10_1038_s41598_023_33033_1
crossref_primary_10_1093_biomet_asaa076
crossref_primary_10_1016_j_worlddev_2022_105924
crossref_primary_10_3389_fbinf_2021_746712
crossref_primary_10_1093_ectj_utaa014
crossref_primary_10_4307_jsee_72_5_75
crossref_primary_10_1080_01621459_2021_1923511
crossref_primary_10_1016_j_jbi_2023_104420
crossref_primary_10_1016_j_jocs_2023_102054
crossref_primary_10_1007_s40593_020_00203_5
crossref_primary_10_1097_EDE_0000000000001684
crossref_primary_10_1177_2158244019851675
crossref_primary_10_1016_j_jbi_2022_104001
crossref_primary_10_1186_s12933_023_01985_3
crossref_primary_10_1007_s00181_024_02575_2
crossref_primary_10_1007_s42519_021_00213_z
crossref_primary_10_1038_s41746_024_01189_3
crossref_primary_10_52396_JUSTC_2022_0054
crossref_primary_10_1007_s11222_024_10434_4
crossref_primary_10_1016_j_dss_2020_113320
crossref_primary_10_1287_isre_2021_0343
crossref_primary_10_1002_cpt_2471
crossref_primary_10_1257_mic_20180336
crossref_primary_10_3390_a16050226
crossref_primary_10_1007_s10489_024_06009_5
crossref_primary_10_3758_s13428_024_02371_x
crossref_primary_10_1145_3722104
crossref_primary_10_1186_s13104_021_05862_8
crossref_primary_10_2139_ssrn_4452778
crossref_primary_10_1016_j_annepidem_2021_07_003
crossref_primary_10_1515_jci_2022_0036
crossref_primary_10_1080_10618600_2022_2026780
crossref_primary_10_1016_j_eswa_2025_126649
crossref_primary_10_1145_3578931
crossref_primary_10_1177_09622802241247728
crossref_primary_10_3389_fneur_2023_1096153
crossref_primary_10_1016_j_xcrm_2025_101947
crossref_primary_10_1109_TKDE_2021_3112591
crossref_primary_10_1086_727597
crossref_primary_10_1142_S0129065723500363
crossref_primary_10_1002_cam4_6666
crossref_primary_10_1080_10618600_2020_1831930
crossref_primary_10_3934_DSFE_2025002
crossref_primary_10_1177_09622802221144326
crossref_primary_10_1214_23_AOAS1799
crossref_primary_10_1080_01621459_2024_2393466
crossref_primary_10_1111_jpc_15975
crossref_primary_10_1007_s10489_022_03860_2
crossref_primary_10_1214_19_BA1195
crossref_primary_10_1161_STROKEAHA_123_044265
crossref_primary_10_3390_ai5040094
crossref_primary_10_1016_j_ins_2023_119578
crossref_primary_10_1097_MD_0000000000039659
crossref_primary_10_1080_01621459_2023_2240461
crossref_primary_10_1093_erae_jbae034
crossref_primary_10_1097_MLR_0000000000001922
crossref_primary_10_1177_09622802251316969
crossref_primary_10_1016_j_dss_2024_114348
crossref_primary_10_1016_j_jsat_2022_108847
crossref_primary_10_1016_j_ejor_2025_02_030
crossref_primary_10_1016_j_giq_2024_101976
crossref_primary_10_1093_cei_uxae104
crossref_primary_10_3389_fmed_2024_1330907
crossref_primary_10_1287_mksc_2022_0379
crossref_primary_10_1007_s11336_021_09805_x
crossref_primary_10_1002_wics_1614
crossref_primary_10_1080_21620555_2021_1948828
crossref_primary_10_1515_jci_2022_0016
crossref_primary_10_1001_jama_2024_3376
crossref_primary_10_1007_s10618_022_00832_5
crossref_primary_10_1038_s41562_023_01555_3
crossref_primary_10_1093_jrsssb_qkaf005
crossref_primary_10_1098_rsos_220638
crossref_primary_10_1056_EVIDoa2300041
crossref_primary_10_3102_1076998620951983
crossref_primary_10_1007_s41060_021_00249_1
crossref_primary_10_2139_ssrn_4847870
crossref_primary_10_1016_j_health_2022_100028
crossref_primary_10_1016_j_is_2023_102198
crossref_primary_10_1038_s41467_022_33269_x
crossref_primary_10_1177_0272989X241289336
crossref_primary_10_1016_j_epsr_2024_110981
crossref_primary_10_1080_10618600_2022_2067549
crossref_primary_10_1111_insr_12427
crossref_primary_10_1002_asmb_2898
crossref_primary_10_1097_MCC_0000000000001186
crossref_primary_10_1007_s13218_023_00803_y
crossref_primary_10_1080_01621459_2020_1772080
crossref_primary_10_1146_annurev_polisci_053119_015921
crossref_primary_10_3389_frai_2022_1015604
crossref_primary_10_1016_j_ejor_2021_05_045
crossref_primary_10_1001_jama_2024_7741
crossref_primary_10_1098_rsta_2022_0153
crossref_primary_10_1109_ACCESS_2023_3333878
crossref_primary_10_1007_s11229_022_03933_2
crossref_primary_10_1287_trsc_2022_0195
crossref_primary_10_1016_j_aap_2022_106811
crossref_primary_10_1080_00273171_2021_1994364
crossref_primary_10_1016_j_jenvman_2025_124514
crossref_primary_10_15388_21_INFOR468
crossref_primary_10_1145_3379500
crossref_primary_10_1016_j_omega_2020_102380
crossref_primary_10_1214_22_EJS2025
crossref_primary_10_3389_fmed_2024_1478842
crossref_primary_10_1136_bmjopen_2021_059715
crossref_primary_10_1097_CCM_0000000000006371
crossref_primary_10_34020_2073_6495_2024_2_081_100
crossref_primary_10_6339_24_JDS1119
crossref_primary_10_2139_ssrn_4129461
crossref_primary_10_1007_s10994_023_06317_w
crossref_primary_10_3390_mca28020032
crossref_primary_10_1007_s11023_024_09691_z
crossref_primary_10_1002_sim_10059
crossref_primary_10_1057_s41599_024_03525_0
crossref_primary_10_1080_10485252_2024_2367674
crossref_primary_10_1093_jrsssa_qnad125
crossref_primary_10_1016_j_ejor_2019_11_030
crossref_primary_10_1109_TVCG_2023_3326587
crossref_primary_10_1007_s00521_023_08221_9
crossref_primary_10_1080_10618600_2024_2418820
crossref_primary_10_1109_TAI_2024_3374269
crossref_primary_10_1214_23_AOS2258
crossref_primary_10_20879_kjjcs_2021_65_6_001
crossref_primary_10_1002_sim_10180
crossref_primary_10_1136_bmj_2024_079377
crossref_primary_10_1515_jqas_2021_0060
crossref_primary_10_1111_rssb_12445
crossref_primary_10_1371_journal_pone_0314761
crossref_primary_10_1002_sim_10186
crossref_primary_10_3389_fmed_2024_1418800
crossref_primary_10_1214_23_STS890
crossref_primary_10_1186_s40854_024_00681_9
crossref_primary_10_1038_s41591_024_02902_1
crossref_primary_10_1016_j_jeconom_2024_105945
crossref_primary_10_1287_mnsc_2023_4819
crossref_primary_10_2139_ssrn_4049267
crossref_primary_10_1109_TIT_2021_3075142
crossref_primary_10_3389_frbhe_2024_1503793
crossref_primary_10_1016_j_cmpb_2024_108017
crossref_primary_10_1016_j_patter_2024_100973
crossref_primary_10_1016_j_ejor_2022_03_049
crossref_primary_10_1080_03610918_2021_1974883
crossref_primary_10_1007_s42521_021_00033_7
crossref_primary_10_1007_s10994_024_06525_y
crossref_primary_10_1145_3444944
crossref_primary_10_1017_psrm_2024_8
crossref_primary_10_1016_j_resconrec_2024_107432
crossref_primary_10_1080_00401706_2022_2142670
crossref_primary_10_1109_ACCESS_2024_3395134
crossref_primary_10_2139_ssrn_3555463
crossref_primary_10_2139_ssrn_3964320
crossref_primary_10_1002_acp_4011
crossref_primary_10_1109_ACCESS_2024_3429359
crossref_primary_10_1136_bmjopen_2022_069298
crossref_primary_10_3390_math12192992
crossref_primary_10_1371_journal_pdig_0000493
crossref_primary_10_2139_ssrn_3875850
crossref_primary_10_1016_j_econlet_2024_111838
crossref_primary_10_1515_jci_2023_0024
crossref_primary_10_1186_s12874_025_02489_2
crossref_primary_10_1016_j_csda_2024_107970
crossref_primary_10_1016_j_dss_2023_114060
crossref_primary_10_1145_3494990
crossref_primary_10_1093_biomtc_ujad012
crossref_primary_10_62347_TRNO3190
crossref_primary_10_1002_cpt_3159
crossref_primary_10_1016_j_jclepro_2025_144913
crossref_primary_10_1002_sim_10167
crossref_primary_10_1016_j_jbi_2022_104086
crossref_primary_10_1146_annurev_soc_030420_015345
crossref_primary_10_1186_s13054_022_03936_y
crossref_primary_10_1002_sim_8926
crossref_primary_10_1017_bpp_2023_35
crossref_primary_10_52396_JUSTC_2023_0033
crossref_primary_10_1055_s_0041_1728757
crossref_primary_10_1007_s10618_021_00797_x
crossref_primary_10_2139_ssrn_3351091
crossref_primary_10_1109_TITS_2024_3421343
crossref_primary_10_1371_journal_pone_0258400
crossref_primary_10_3103_S0005105524700249
crossref_primary_10_1177_10949968221111083
crossref_primary_10_2196_50890
crossref_primary_10_1017_pan_2019_34
crossref_primary_10_1111_1475_6773_13586
crossref_primary_10_1007_s12094_024_03459_8
crossref_primary_10_1186_s12874_020_01145_1
crossref_primary_10_1016_j_tbs_2024_100852
crossref_primary_10_2139_ssrn_3666456
crossref_primary_10_3390_e24121782
crossref_primary_10_1007_s10994_024_06546_7
crossref_primary_10_1109_ACCESS_2024_3437665
crossref_primary_10_1080_15481603_2024_2321695
crossref_primary_10_1109_TLT_2023_3264772
crossref_primary_10_3102_10769986231155427
crossref_primary_10_1016_j_ins_2022_08_024
crossref_primary_10_1038_s41467_023_41011_4
crossref_primary_10_1177_00491241241234866
crossref_primary_10_1016_j_ssmph_2025_101764
crossref_primary_10_7326_M22_1510
crossref_primary_10_1111_biom_13837
crossref_primary_10_2139_ssrn_4514424
crossref_primary_10_1001_jamanetworkopen_2020_29050
crossref_primary_10_3390_s23042265
crossref_primary_10_1016_j_eneco_2024_107768
crossref_primary_10_1002_widm_1449
crossref_primary_10_1038_s41598_025_88433_2
crossref_primary_10_1007_s10994_023_06421_x
crossref_primary_10_1145_3656639
crossref_primary_10_1007_s10994_024_06729_2
crossref_primary_10_1002_jae_3092
crossref_primary_10_1507_endocrj_EJ24_0193
crossref_primary_10_3390_a17070318
crossref_primary_10_1002_sim_9100
crossref_primary_10_1016_j_ssmph_2021_100836
crossref_primary_10_1177_25152459241236149
crossref_primary_10_1200_JCO_21_01957
crossref_primary_10_1016_j_infsof_2023_107198
crossref_primary_10_1161_HYPERTENSIONAHA_124_22095
crossref_primary_10_1007_s10654_022_00901_5
crossref_primary_10_1017_rsm_2025_5
crossref_primary_10_1155_2023_2081588
crossref_primary_10_1109_TBDATA_2023_3291547
crossref_primary_10_1016_j_chb_2023_108080
crossref_primary_10_1016_j_compbiomed_2024_108995
crossref_primary_10_1016_j_dss_2021_113648
crossref_primary_10_1093_aje_kwae003
crossref_primary_10_1093_ectj_utac015
crossref_primary_10_1016_j_cardfail_2025_01_027
crossref_primary_10_3389_fneur_2024_1326591
crossref_primary_10_1093_aje_kwae008
crossref_primary_10_1177_10659129231224084
crossref_primary_10_1080_01621459_2020_1844210
crossref_primary_10_1016_j_apenergy_2023_121783
crossref_primary_10_1016_j_spl_2023_109854
crossref_primary_10_2196_67210
crossref_primary_10_1016_j_joi_2022_101283
crossref_primary_10_1016_j_jeconom_2022_07_006
crossref_primary_10_1016_j_ajcnut_2023_05_006
crossref_primary_10_1007_s10618_019_00670_y
crossref_primary_10_1007_s00432_023_05602_4
crossref_primary_10_1016_j_asoc_2021_107241
crossref_primary_10_1007_s10488_023_01303_9
crossref_primary_10_1111_rssa_12824
crossref_primary_10_1016_j_jbi_2023_104339
crossref_primary_10_1007_s10614_024_10722_1
crossref_primary_10_1080_01621459_2020_1811099
crossref_primary_10_1002_cpt_3627
crossref_primary_10_1186_s12879_021_06812_2
crossref_primary_10_2139_ssrn_3048177
crossref_primary_10_2139_ssrn_4254202
crossref_primary_10_1140_epjds_s13688_022_00361_7
crossref_primary_10_1177_0272989X221100717
crossref_primary_10_1214_23_AOAS1740
crossref_primary_10_3390_data10020018
crossref_primary_10_1002_joom_1240
crossref_primary_10_1287_mnsc_2020_3699
crossref_primary_10_1080_03155986_2024_2383095
crossref_primary_10_1080_23311916_2023_2300557
crossref_primary_10_1016_j_egyai_2025_100487
crossref_primary_10_1017_pan_2021_19
crossref_primary_10_1002_pds_5500
crossref_primary_10_1097_ADM_0000000000001313
crossref_primary_10_1007_s10618_024_01042_x
crossref_primary_10_1177_17407745231174544
crossref_primary_10_3390_a17010040
crossref_primary_10_1002_hed_27938
crossref_primary_10_1093_jrsssb_qkac001
crossref_primary_10_1177_09622802211052831
crossref_primary_10_1360_SSM_2023_0246
crossref_primary_10_1109_ACCESS_2024_3376423
crossref_primary_10_1111_biom_13800
crossref_primary_10_1017_pan_2021_30
crossref_primary_10_3102_10769986231162096
crossref_primary_10_1016_j_compbiomed_2024_108779
crossref_primary_10_1145_3466818
crossref_primary_10_1002_sim_9812
crossref_primary_10_2139_ssrn_4212172
crossref_primary_10_1111_aas_14492
crossref_primary_10_1111_jels_12333
crossref_primary_10_1007_s10618_023_00917_9
crossref_primary_10_1007_s10742_021_00259_3
crossref_primary_10_1093_gigascience_giaf016
crossref_primary_10_1017_dap_2024_35
crossref_primary_10_1093_polsoc_puad030
crossref_primary_10_2139_ssrn_4590356
crossref_primary_10_1080_03155986_2024_2386494
crossref_primary_10_1002_sim_9010
crossref_primary_10_2139_ssrn_4746623
Cites_doi 10.1093/biomet/70.1.41
10.1017/S000305540808009X
10.1214/ss/1177012031
10.1037/h0037350
10.1017/S0003055417000363
10.1214/09-AOAS285
10.1007/s11109-010-9124-y
10.1080/01621459.2014.951443
10.1007/b13794
10.1214/aos/1176345969
10.1017/pan.2017.27
10.1080/01621459.2017.1319839
10.1017/S104909651600024X
10.1073/pnas.1510489113
10.1198/jcgs.2010.08162
10.1126/science.aad9713
10.1093/poq/nfs036
10.1198/jasa.2009.ap06589
10.1214/15-AOS1321
ContentType Journal Article
Copyright Copyright © 2019 the Author(s). Published by PNAS.
Copyright National Academy of Sciences Mar 5, 2019
Copyright © 2019 the Author(s). Published by PNAS. 2019
Copyright_xml – notice: Copyright © 2019 the Author(s). Published by PNAS.
– notice: Copyright National Academy of Sciences Mar 5, 2019
– notice: Copyright © 2019 the Author(s). Published by PNAS. 2019
CorporateAuthor Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
CorporateAuthor_xml – sequence: 0
  name: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
DBID AAYXX
CITATION
NPM
7QG
7QL
7QP
7QR
7SN
7SS
7T5
7TK
7TM
7TO
7U9
8FD
C1K
FR3
H94
M7N
P64
RC3
7X8
OIOZB
OTOTI
5PM
ADTOC
UNPAY
DOI 10.1073/pnas.1804597116
DatabaseName CrossRef
PubMed
Animal Behavior Abstracts
Bacteriology Abstracts (Microbiology B)
Calcium & Calcified Tissue Abstracts
Chemoreception Abstracts
Ecology Abstracts
Entomology Abstracts (Full archive)
Immunology Abstracts
Neurosciences Abstracts
Nucleic Acids Abstracts
Oncogenes and Growth Factors Abstracts
Virology and AIDS Abstracts
Technology Research Database
Environmental Sciences and Pollution Management
Engineering Research Database
AIDS and Cancer Research Abstracts
Algology Mycology and Protozoology Abstracts (Microbiology C)
Biotechnology and BioEngineering Abstracts
Genetics Abstracts
MEDLINE - Academic
OSTI.GOV - Hybrid
OSTI.GOV
PubMed Central (Full Participant titles)
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
PubMed
Virology and AIDS Abstracts
Oncogenes and Growth Factors Abstracts
Technology Research Database
Nucleic Acids Abstracts
Ecology Abstracts
Neurosciences Abstracts
Biotechnology and BioEngineering Abstracts
Environmental Sciences and Pollution Management
Entomology Abstracts
Genetics Abstracts
Animal Behavior Abstracts
Bacteriology Abstracts (Microbiology B)
Algology Mycology and Protozoology Abstracts (Microbiology C)
AIDS and Cancer Research Abstracts
Chemoreception Abstracts
Immunology Abstracts
Engineering Research Database
Calcium & Calcified Tissue Abstracts
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
Virology and AIDS Abstracts

CrossRef


PubMed
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Sciences (General)
Statistics
Political Science
Engineering
EISSN 1091-6490
EndPage 4165
ExternalDocumentID 10.1073/pnas.1804597116
PMC6410831
1604674
30770453
10_1073_pnas_1804597116
26683078
Genre Research Article
Research Support, U.S. Gov't, Non-P.H.S
Journal Article
GrantInformation_xml – fundername: National Science Foundation (NSF)
  grantid: DMS 1713083
– fundername: DOD | United States Navy | Office of Naval Research (ONR)
  grantid: N00014-15-1-2367
– fundername: DOD | United States Army | RDECOM | Army Research Office (ARO)
  grantid: W911NF-17-10005
– fundername: DOD | United States Navy | Office of Naval Research (ONR)
  grantid: N00014-16-1-2664
– fundername: DOD | United States Navy | Office of Naval Research (ONR)
  grantid: N00014-17-1-2176
– fundername: Center of Science of Information | National Science Foundation
  grantid: CCF-0939370
GroupedDBID ---
-DZ
-~X
.55
0R~
123
29P
2AX
2FS
2WC
4.4
53G
5RE
5VS
85S
AACGO
AAFWJ
AANCE
ABBHK
ABOCM
ABPLY
ABPPZ
ABTLG
ABXSQ
ABZEH
ACGOD
ACHIC
ACIWK
ACNCT
ACPRK
ADQXQ
ADULT
AENEX
AEUPB
AEXZC
AFFNX
AFOSN
AFRAH
ALMA_UNASSIGNED_HOLDINGS
AQVQM
BKOMP
CS3
D0L
DCCCD
DIK
DU5
E3Z
EBS
EJD
F5P
FRP
GX1
H13
HH5
HYE
IPSME
JAAYA
JBMMH
JENOY
JHFFW
JKQEH
JLS
JLXEF
JPM
JSG
JST
KQ8
L7B
LU7
N9A
N~3
O9-
OK1
PNE
PQQKQ
R.V
RHI
RNA
RNS
RPM
RXW
SA0
SJN
TAE
TN5
UKR
W8F
WH7
WOQ
WOW
X7M
XSW
Y6R
YBH
YKV
YSK
ZCA
~02
~KM
AAYXX
CITATION
NPM
7QG
7QL
7QP
7QR
7SN
7SS
7T5
7TK
7TM
7TO
7U9
8FD
C1K
FR3
H94
M7N
P64
RC3
7X8
ADACV
DOOOF
JSODD
OIOZB
OTOTI
RHF
VQA
5PM
.GJ
3O-
692
6TJ
79B
AAYJJ
ACKIV
ADTOC
ADXHL
AFHIN
AFQQW
AS~
HGD
HQ3
HTVGU
MVM
NEJ
NHB
P-O
UNPAY
VOH
WHG
ZCG
ID FETCH-LOGICAL-c572t-db9af8afc7e1714e9818c01a005754b0659785d90aa9cb7505e1f250a7917f3a3
IEDL.DBID UNPAY
ISSN 0027-8424
1091-6490
IngestDate Wed Oct 29 12:04:15 EDT 2025
Tue Sep 30 16:58:59 EDT 2025
Thu Dec 05 06:23:55 EST 2024
Fri Sep 05 12:17:26 EDT 2025
Mon Jun 30 08:22:51 EDT 2025
Thu Apr 03 06:55:00 EDT 2025
Wed Oct 01 04:16:21 EDT 2025
Thu Apr 24 22:55:12 EDT 2025
Thu Oct 09 22:07:39 EDT 2025
Thu May 29 13:25:11 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 10
IssueTitle PNAS Plus
Keywords conditional average treatment effect
minimax optimality
observational studies
randomized controlled trials
heterogeneous treatment effects
Language English
License https://creativecommons.org/licenses/by-nc-nd/4.0
Copyright © 2019 the Author(s). Published by PNAS.
This open access article is distributed under Creative Commons Attribution-NonCommercial-NoDerivatives License 4.0 (CC BY-NC-ND).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c572t-db9af8afc7e1714e9818c01a005754b0659785d90aa9cb7505e1f250a7917f3a3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
AC02-05CH11231; N00014-17-1-2176; N00014-15-2367; N00014-16-1-2664; DMS 1713083; W911NF-17-10005; CCF-0939370
USDOE Office of Science (SC)
National Science Foundation (NSF)
US Department of the Navy, Office of Naval Research (ONR)
US Army Research Office (ARO)
Contributed by Bin Yu, December 18, 2018 (sent for review March 16, 2018; reviewed by Jake Bowers and Dylan Small)
Reviewers: J.B., University of Illinois at Urbana–Champaign; and D.S., Wharton School, University of Pennsylvania.
Author contributions: S.R.K., J.S.S., P.J.B., and B.Y. designed research, performed research, analyzed data, and wrote the paper.
OpenAccessLink https://proxy.k.utb.cz/login?url=https://www.pnas.org/content/pnas/116/10/4156.full.pdf
PMID 30770453
PQID 2194120961
PQPubID 42026
PageCount 10
ParticipantIDs unpaywall_primary_10_1073_pnas_1804597116
pubmedcentral_primary_oai_pubmedcentral_nih_gov_6410831
osti_scitechconnect_1604674
proquest_miscellaneous_2200767401
proquest_journals_2194120961
pubmed_primary_30770453
crossref_citationtrail_10_1073_pnas_1804597116
crossref_primary_10_1073_pnas_1804597116
pnas_primary_10_1073_pnas_1804597116
jstor_primary_26683078
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2019-03-05
PublicationDateYYYYMMDD 2019-03-05
PublicationDate_xml – month: 03
  year: 2019
  text: 2019-03-05
  day: 05
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Washington
PublicationSeriesTitle PNAS Plus
PublicationTitle Proceedings of the National Academy of Sciences - PNAS
PublicationTitleAbbrev Proc Natl Acad Sci USA
PublicationTitleAlternate Proc Natl Acad Sci U S A
PublicationYear 2019
Publisher National Academy of Sciences
Publisher_xml – sequence: 0
  name: National Academy of Sciences
– name: National Academy of Sciences
References Powers 2017
Green, Kern 2012; 76
Künzel, Tang, Bickel, Yu, Sekhon 2017
Michelson 2016; 49
Athey, Imbens 2016; 113
Scornet, Biau, Vert 2015; 43
Wager, Athey 2017; 113
Broockman, Kalla, Sekhon 2017; 25
Hill 2011; 20
Kalla, Broockman 2018; 112
Splawa-Neyman, Dabrowska, Speed 1990; 5
Bickel, Doksum 2015; Vol 2
Chipman, George, McCulloch R 2010; 4
Hájek 1967; Vol 1
Le Cam 1956; Vol 1
Tsybakov 2009
Györfi, Kohler, Krzyzak, Walk 2006
Rosenbaum, Rubin 1983; 70
Rubin 1974; 66
Stone 1982; 10
Hansen, Bowers 2009; 104
Tian, Alizadeh, Gentles, Tibshirani 2014; 109
Broockman, Kalla, Aronow 2015
Mann 2010; 32
Gerber, Green, Larimer 2008; 102
Broockman, Kalla 2016; 352
Foster 2013
Sekhon, Shem-Tov 2017
Hájek J (e_1_3_3_22_2) 1967
Bickel PJ (e_1_3_3_21_2) 2015
Györfi L (e_1_3_3_19_2) 2006
e_1_3_3_17_2
e_1_3_3_16_2
e_1_3_3_18_2
e_1_3_3_13_2
e_1_3_3_12_2
e_1_3_3_15_2
e_1_3_3_14_2
e_1_3_3_11_2
e_1_3_3_10_2
Le Cam L (e_1_3_3_23_2) 1956
e_1_3_3_6_2
e_1_3_3_5_2
e_1_3_3_8_2
e_1_3_3_7_2
e_1_3_3_28_2
e_1_3_3_9_2
e_1_3_3_27_2
e_1_3_3_24_2
e_1_3_3_26_2
e_1_3_3_25_2
e_1_3_3_2_2
e_1_3_3_20_2
e_1_3_3_1_2
e_1_3_3_4_2
e_1_3_3_3_2
References_xml – volume: 5
  start-page: 465
  year: 1990
  end-page: 472
  article-title: On the application of probability theory to agricultural experiments
  publication-title: Stat Sci
– volume: Vol 1
  start-page: 129
  year: 1956
  end-page: 156
  publication-title: On the asymptotic theory of estimation and testing hypotheses. Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability
– volume: 76
  start-page: 491
  year: 2012
  end-page: 511
  article-title: Modeling heterogeneous treatment effects in survey experiments with Bayesian additive regression trees
  publication-title: Public Opin Q
– volume: Vol 1
  start-page: 139
  year: 1967
  end-page: 162
  publication-title: On basic concepts of statistics. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probabilities
– volume: 112
  start-page: 148
  year: 2018
  end-page: 166
  article-title: The minimal persuasive effects of campaign contact in general elections: Evidence from 49 field experiments
  publication-title: Am Polit Sci Rev
– year: 2017
– volume: 66
  start-page: 688
  year: 1974
  end-page: 701
  article-title: Estimating causal effects of treatments in randomized and nonrandomized studies
  publication-title: J Educ Psychol
– volume: 25
  start-page: 435
  year: 2017
  end-page: 464
  article-title: The design of field experiments with survey outcomes: A framework for selecting more efficient, robust, and ethical designs
  publication-title: Polit Anal
– volume: 113
  start-page: 1228
  year: 2017
  end-page: 1242
  article-title: Estimation and inference of heterogeneous treatment effects using random forests
  publication-title: J Am Stat Assoc
– volume: 20
  start-page: 217
  year: 2011
  end-page: 240
  article-title: Bayesian nonparametric modeling for causal inference
  publication-title: J Comput Graphical Stat
– volume: 10
  start-page: 1040
  year: 1982
  end-page: 1053
  article-title: Optimal global rates of convergence for nonparametric regression
  publication-title: Ann Stat
– volume: 102
  start-page: 33
  year: 2008
  end-page: 48
  article-title: Social pressure and voter turnout: Evidence from a large-scale field experiment
  publication-title: Am Polit Sci Rev
– year: 2017
– year: 2006
  publication-title: A Distribution-Free Theory of Nonparametric Regression
– volume: 352
  start-page: 220
  year: 2016
  end-page: 224
  article-title: Durably reducing transphobia: A field experiment on door-to-door canvassing
  publication-title: Science
– year: 2017
– year: 2015
– volume: 104
  start-page: 873
  year: 2009
  end-page: 885
  article-title: Attributing effects to a cluster-randomized get-out-the-vote campaign
  publication-title: J Am Stat Assoc
– volume: 113
  start-page: 7353
  year: 2016
  end-page: 7360
  article-title: Recursive partitioning for heterogeneous causal effects
  publication-title: Proc Natl Acad Sci USA
– volume: 109
  start-page: 1517
  year: 2014
  end-page: 1532
  article-title: A simple method for estimating interactions between a treatment and a large number of covariates
  publication-title: J Am Stat Assoc
– year: 2009
– volume: 49
  start-page: 299
  year: 2016
  end-page: 303
  article-title: The risk of over-reliance on the institutional review board: An approved project is not always an ethical project
  publication-title: PS Polit Sci Polit
– volume: 43
  start-page: 1716
  year: 2015
  end-page: 1741
  article-title: Consistency of random forests
  publication-title: Ann Stat
– volume: 4
  start-page: 266
  year: 2010
  end-page: 298
  article-title: BART: Bayesian additive regression trees
  publication-title: Ann Appl Stat
– volume: Vol 2
  year: 2015
  publication-title: Mathematical Statistics: Basic Ideas and Selected Topics
– volume: 32
  start-page: 387
  year: 2010
  end-page: 407
  article-title: Is there backlash to social pressure? A large-scale field experiment on voter mobilization
  publication-title: Polit Behav
– year: 2013
– volume: 70
  start-page: 41
  year: 1983
  end-page: 55
  article-title: The central role of the propensity score in observational studies for causal effects
  publication-title: Biometrika
– ident: e_1_3_3_3_2
– ident: e_1_3_3_13_2
  doi: 10.1093/biomet/70.1.41
– ident: e_1_3_3_1_2
  doi: 10.1017/S000305540808009X
– ident: e_1_3_3_15_2
– ident: e_1_3_3_12_2
  doi: 10.1214/ss/1177012031
– start-page: 139
  volume-title: On basic concepts of statistics. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probabilities
  year: 1967
  ident: e_1_3_3_22_2
– ident: e_1_3_3_11_2
  doi: 10.1037/h0037350
– ident: e_1_3_3_9_2
  doi: 10.1017/S0003055417000363
– ident: e_1_3_3_18_2
  doi: 10.1214/09-AOAS285
– volume-title: A Distribution-Free Theory of Nonparametric Regression
  year: 2006
  ident: e_1_3_3_19_2
– ident: e_1_3_3_25_2
  doi: 10.1007/s11109-010-9124-y
– ident: e_1_3_3_14_2
  doi: 10.1080/01621459.2014.951443
– ident: e_1_3_3_20_2
  doi: 10.1007/b13794
– ident: e_1_3_3_24_2
  doi: 10.1214/aos/1176345969
– ident: e_1_3_3_28_2
  doi: 10.1017/pan.2017.27
– ident: e_1_3_3_10_2
– ident: e_1_3_3_8_2
  doi: 10.1080/01621459.2017.1319839
– ident: e_1_3_3_26_2
  doi: 10.1017/S104909651600024X
– ident: e_1_3_3_4_2
  doi: 10.1073/pnas.1510489113
– start-page: 129
  volume-title: On the asymptotic theory of estimation and testing hypotheses. Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability
  year: 1956
  ident: e_1_3_3_23_2
– ident: e_1_3_3_5_2
  doi: 10.1198/jcgs.2010.08162
– ident: e_1_3_3_2_2
  doi: 10.1126/science.aad9713
– ident: e_1_3_3_16_2
– ident: e_1_3_3_6_2
  doi: 10.1093/poq/nfs036
– ident: e_1_3_3_7_2
  doi: 10.1198/jasa.2009.ap06589
– ident: e_1_3_3_17_2
  doi: 10.1214/15-AOS1321
– ident: e_1_3_3_27_2
– volume-title: Mathematical Statistics: Basic Ideas and Selected Topics
  year: 2015
  ident: e_1_3_3_21_2
SSID ssj0009580
Score 2.7215252
Snippet There is growing interest in estimating and analyzing heterogeneous treatment effects in experimental and observational studies. We describe a number of...
SignificanceEstimating and analyzing heterogeneous treatment effects is timely, yet challenging. We introduce a unifying framework for many conditional average...
Estimating and analyzing heterogeneous treatment effects is timely, yet challenging. We introduce a unifying framework for many conditional average treatment...
SourceID unpaywall
pubmedcentral
osti
proquest
pubmed
crossref
pnas
jstor
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 4156
SubjectTerms Algorithms
Artificial intelligence
Bayesian analysis
Computer simulation
conditional average treatment
effect
ENGINEERING
Estimation
Field tests
heterogeneous treatment effects
Learning algorithms
Machine learning
minimax optimality
Neural networks
Observational studies
Physical Sciences
PNAS Plus
Political science
Political Sciences
randomized controlled trials
Regression analysis
Response functions
Social Sciences
Statistics
Title Metalearners for estimating heterogeneous treatment effects using machine learning
URI https://www.jstor.org/stable/26683078
https://www.pnas.org/doi/10.1073/pnas.1804597116
https://www.ncbi.nlm.nih.gov/pubmed/30770453
https://www.proquest.com/docview/2194120961
https://www.proquest.com/docview/2200767401
https://www.osti.gov/servlets/purl/1604674
https://pubmed.ncbi.nlm.nih.gov/PMC6410831
https://www.pnas.org/content/pnas/116/10/4156.full.pdf
UnpaywallVersion publishedVersion
Volume 116
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVFSB
  databaseName: Free Full-Text Journals in Chemistry
  customDbUrl:
  eissn: 1091-6490
  dateEnd: 20250503
  omitProxy: true
  ssIdentifier: ssj0009580
  issn: 0027-8424
  databaseCode: HH5
  dateStart: 19150101
  isFulltext: true
  titleUrlDefault: http://abc-chemistry.org/
  providerName: ABC ChemistRy
– providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1091-6490
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0009580
  issn: 0027-8424
  databaseCode: KQ8
  dateStart: 19150101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1091-6490
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0009580
  issn: 0027-8424
  databaseCode: KQ8
  dateStart: 19150115
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVBFR
  databaseName: Free Medical Journals
  customDbUrl:
  eissn: 1091-6490
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0009580
  issn: 0027-8424
  databaseCode: DIK
  dateStart: 19150101
  isFulltext: true
  titleUrlDefault: http://www.freemedicaljournals.com
  providerName: Flying Publisher
– providerCode: PRVFQY
  databaseName: GFMER Free Medical Journals
  customDbUrl:
  eissn: 1091-6490
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0009580
  issn: 0027-8424
  databaseCode: GX1
  dateStart: 0
  isFulltext: true
  titleUrlDefault: http://www.gfmer.ch/Medical_journals/Free_medical.php
  providerName: Geneva Foundation for Medical Education and Research
– providerCode: PRVAQN
  databaseName: PubMed Central
  customDbUrl:
  eissn: 1091-6490
  dateEnd: 20250503
  omitProxy: true
  ssIdentifier: ssj0009580
  issn: 0027-8424
  databaseCode: RPM
  dateStart: 19150101
  isFulltext: true
  titleUrlDefault: https://www.ncbi.nlm.nih.gov/pmc/
  providerName: National Library of Medicine
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwED5t3QO8DAYMwsZkpD1sD0njJrHjxwkxJqRNCFFRniLHtbuJklZrKgR_PXfODzZ-aNprc3Xq-nz32f78HcDhKBGYdKUJnbY2TPmUhwqzZDiyLpFKmVx5-eLzC3E2Tt9PsskGiO4uDNEql5Ve-UN8Ymtj6B3SB0POBU7xIS04ItqajpZTtwlbIkMMPoCt8cWHky8NnwPDbtpUs8VkGIpUxZ2mj0x8WxHPEckoyanK-Y101DASMTgvcHqR2ina_gt5_k2gfLCulvrHdz2f38hOp4_gc9evhpTyNVrXZWR-_iH5eP-OP4btFrCyk8bDdmDDVk9gpw0JK3bU6lYfP4WP5xaRPG21IKRkCIYZKXgQIq5m7JJoNwv0VrtYr1hPb2ctn4QR_37Gvnlqp2VtLYvZMxifvv305ixsSzaEJpOjOpyWSrtcOyMtVVa3CvGAibmmO69ZWtIhrsyzqYq1VqZEtJJZ7hCFaYnLRpfoZBcG1aKyL4DFpc10aUrhcMWojVMJaaulbuol8LUNIOpGrjCtnjmV1ZgX_lxdJgX9e8XvoQ7gqP_CspHy-L_prneF3g5hTI7RMA9gj3yjQHhCGruGyEimLriIqWpLAIe-oTtb3-9cqmgjxqrAzJHSPWbBA3jdP8a5Tgc42g9OMaKNZUE1FAN43nhg_y78dRJfkAQgb_lmb0A64refVFeXXk9cpJzqzQVw3HvxXV14eQ_bPXiIKFN54l62D4P6em1fIZKrywPYfDfhB-3k_QX23US1
linkProvider Unpaywall
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fb9MwED6N7gFeGAMG2QYy0h62h6Rxk9jx4zQxTUibEKJiPEWOY3eIklY0FYK_fnfODzZ-aNprc3Xq-nz32f78HcDBJBGYdKUJnbY2THnFQ4VZMpxYl0ilTK68fPH5hTibpu8us8sNEP1dGKJVLmu98of4xNbG0DumD8acC5ziY1pwRLQ1HS0r9wA2RYYYfASb04v3x59bPgeG3bStZovJMBSpintNH5n4tiKeI5JRklOV8xvpqGUkYnBe4PQitVO0_Rfy_JtA-XBdL_XPH3o-v5GdTrfgU9-vlpTyNVo3ZWR-_SH5eP-OP4HHHWBlx62HbcOGrZ_CdhcSVuyw060-egYfzi0iedpqQUjJEAwzUvAgRFzP2BXRbhborXaxXrGB3s46Pgkj_v2MffPUTsu6Whaz5zA9ffvx5CzsSjaEJpOTJqxKpV2unZGWKqtbhXjAxFzTndcsLekQV-ZZpWKtlSkRrWSWO0RhWuKy0SU62YFRvajtS2BxaTNdmlI4XDFq41RC2mqpq7wEvrYBRP3IFabTM6eyGvPCn6vLpKB_r_g91AEcDl9YtlIe_zfd8a4w2CGMyTEa5gHskW8UCE9IY9cQGck0BRcxVW0J4MA3dGfr-71LFV3EWBWYOVK6xyx4AG-GxzjX6QBH-8EpJrSxLKiGYgAvWg8c3oW_TuILkgDkLd8cDEhH_PaT-suV1xMXKad6cwEcDV58Vxd272G7B48QZSpP3Mv2YdR8X9tXiOSa8nU3ba8BYFhDxA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Metalearners+for+estimating+heterogeneous+treatment+effects+using+machine+learning&rft.jtitle=Proceedings+of+the+National+Academy+of+Sciences+-+PNAS&rft.au=K%C3%BCnzel%2C+S%C3%B6ren+R&rft.au=Sekhon%2C+Jasjeet+S&rft.au=Bickel%2C+Peter+J&rft.au=Yu%2C+Bin&rft.date=2019-03-05&rft.eissn=1091-6490&rft.volume=116&rft.issue=10&rft.spage=4156&rft_id=info:doi/10.1073%2Fpnas.1804597116&rft_id=info%3Apmid%2F30770453&rft.externalDocID=30770453
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0027-8424&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0027-8424&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0027-8424&client=summon