{"args":{},"checks":[{"abs_tol":null,"bind":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"answer_backed","min_lre":null,"note":"every number in the answer was stated by a tool call","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":null,"value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"answer_call","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"answer_figure_close","min_lre":null,"note":"CauSciBench effect accuracy: |answer figure \u2212 gold| \u2264 5% of |gold|","open_interval":false,"rel_tol":0.05,"required":true,"source_id":"causcibench_real.gold.q005","table":null,"tool":null,"value":1672.204,"weight":1.0,"where":null}],"datasets":{"dehejia_propensity_score":{"columns":null,"description":"The data originates from the National Supported Work (NSW) Demonstration, which was a temporary employment program created to assist disadvantaged workers lacking basic job skills in entering the labor market. The NSW program randomly assigned qualified applicants to either a treatment group, which received the benefits of the NSW program, or a control group, which did not. Participants in the treatment group were guaranteed a job for a duration of 9 to 18 months.\nVariables Measured:\ntreat: whether the applicant received the training (1 if received training, 0 otherwise)\nage: measured in years\neducation: measured in years\nblack: indicating race (1 if Black, 0 otherwise)\nhispanic: indicating race (1 if Hispanic, 0 otherwise)\nmarried: indicating marital status (1 if married, 0 otherwise)\nnodegree: indicating high school diploma (1 if no degree, 0 otherwise)\nre74: real earnings in 1974\nre75: real earnings in 1975\nre78: real earnings in 1978","file_sha256":"301ac38a23accac1694b5be91c3967dc22fc38c70c3a82ab4d67786194a816eb","format":"csv","frame_sha256":null,"generator":null,"kind":"file","licence":"CC BY-NC 2.0 (CauSciBench data/README.md); original source https://users.nber.org/~rdehejia/data/.nswdata2.html","member":null,"object":null,"params":{},"path":null,"read_kw":{},"records":null,"role":"agent","sha256":"301ac38a23accac1694b5be91c3967dc22fc38c70c3a82ab4d67786194a816eb","transforms":[],"url":"https://huggingface.co/datasets/causal-nlp/causcibench/resolve/d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a/csv_files/realdata/dehejia_propensity_score.csv"}},"difficulty":"M","id":"causcibench_real.q005","level":"T2","meta":{"agent_reach":{"blocked_by":[],"dtypes":{"dehejia_propensity_score":{"age":"int64","black":"int64","education":"int64","hispanic":"int64","nodegree":"int64","re74":"float64","re75":"float64","re78":"float64","treat":"int64"}},"named":{"outcome":["re78"],"treatment":["treat"]},"reachable":true,"rule":"magi_bench.reach/1"},"answer_format":{"figure_transform":"identity","round_to":null,"unit_scale":1.0},"cluster":"paper:Propensity score matching for methods for non-experimental causal studies","gold":{"effect":1672.204,"effect_as_stored":"1672.204","is_significant":1,"source_id":"causcibench_real.gold.q005","std_error":638.397,"std_error_as_stored":"638.397"},"headline_keys":{"infer.ols":["coef.treat"]},"metadata":{"control_variables":"age,education,black,hispanic,nodegree,re74,re75","dataset_path":"data/csv_files/realdata/dehejia_propensity_score.csv","effect":1672.204,"id":5,"instrument_var":null,"interaction_var":null,"is_rct":true,"is_significant":1,"method":"ols","name":"Propensity score matching for methods for non-experimental causal studies","outcome_var":"re78","running_var":null,"state_var":null,"std_error":638.397,"temporal_var":null,"treatment_var":"treat"},"naive":{"dataset":"dehejia_propensity_score","treatment":"treat","y":"re78"},"name":"Propensity score matching for methods for non-experimental causal studies","native_id":5,"outcome":"re78","pin":{"data_repo":"causal-nlp/causcibench","data_revision":"d8aca99042e0bf1d73120a9dc1b65d4079fa1c3a","repo":"causalNLP/CauSciBench","revision":"d9bb43a2d90f261978cc5ac0b628c0484f6e8956"},"precision_limited":false,"reference":{"cite":1,"steps":[{"args":{"controls":["age","education","black","hispanic","nodegree","re74","re75"],"dataset":"dehejia_propensity_score","x":["treat"],"y":"re78"},"tool":"infer.ols","why":"causcibench_metadata_rule/1: ols"}]},"reference_notes":[],"reference_path":{"calls":[{"args":{"controls":["age","education","black","hispanic","nodegree","re74","re75"],"dataset":"dehejia_propensity_score","x":["treat"],"y":"re78"},"tool":"infer.ols"}],"needs":[],"provenance":"metadata_rule","quotes":{},"reference_datasets":[],"source_id":null},"reference_rule":"causcibench_metadata_rule/1","source":"causcibench","treatment":"treat"},"question":"What is the effect of the training program on job earnings for 1978?","requires":[],"runner":null,"sources":["causcibench_real.gold.q005"],"split":"public","suite":"causcibench_real","tags":["econ-bench","external","causcibench","method:ols"],"target":"agent","tool":null,"truth":"CauSciBench real_input.json @ d9bb43a, id 5: effect 1672.204"}