{"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":"","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":"any","column":null,"failure_class":null,"field":"value","interval":false,"key":null,"kind":"answer_cites","min_lre":null,"note":"the answer cites a figure of a data.describe call (no citation: no_estimate_cited)","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":"data.describe","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":"tool_called","min_lre":null,"note":"","open_interval":false,"rel_tol":null,"required":true,"source_id":null,"table":null,"tool":"data.describe","value":null,"weight":1.0,"where":null},{"abs_tol":null,"bind":"answer_call","column":"mean","failure_class":null,"field":"value","interval":false,"key":null,"kind":"table_close","min_lre":null,"note":"certified sample mean; rel_tol 1e-09 is the bound LRE >= 9","open_interval":false,"rel_tol":1e-09,"required":true,"source_id":"nist_univariate.lew.mean","table":"columns","tool":"data.describe","value":-177.435,"weight":1.0,"where":{"column":"y"}},{"abs_tol":null,"bind":"answer_call","column":"sd","failure_class":null,"field":"value","interval":false,"key":null,"kind":"table_close","min_lre":null,"note":"certified sample standard deviation (n \u2212 1); rel_tol 1e-09 is the bound LRE >= 9","open_interval":false,"rel_tol":1e-09,"required":true,"source_id":"nist_univariate.lew.sd","table":"columns","tool":"data.describe","value":277.332168044316,"weight":1.0,"where":{"column":"y"}}],"datasets":{"d":{"columns":["y"],"description":"NIST StRD Lew: 200 observations of y, one per row","file_sha256":"53cdc7d066ed1dd726528b4bdd8c51034d37fff6709195de8a0013e5131340e4","format":"whitespace","frame_sha256":null,"generator":null,"kind":"file","licence":"Public domain (US Government work, NIST)","member":null,"object":null,"params":{},"path":null,"read_kw":{"float_precision":"round_trip","quoting":3,"skiprows":60},"records":null,"role":"agent","sha256":"53cdc7d066ed1dd726528b4bdd8c51034d37fff6709195de8a0013e5131340e4","transforms":[],"url":"https://web.archive.org/web/20010211025406id_/http://www.itl.nist.gov/div898/strd/univ/data/Lew.dat"}},"difficulty":"E","id":"nist_univariate.lew.agent","level":"T2","meta":{"cluster":"53cdc7d066ed1dd726528b4bdd8c51034d37fff6709195de8a0013e5131340e4","difficulty":"lower","double_frame_lre":{"mean":15.0,"sd":15.0},"expected_tool":"data.describe","gold_kind":"derived","min_lre":9.0,"native_id":"Lew","problem":"Lew","question_omits":["r(1), the lag-1 autocorrelation NIST also certifies: no tool states it"],"reference":{"cite":1,"steps":[{"args":{"columns":["y"],"dataset":"d"},"tool":"data.describe","why":"Describe y: the table states its mean and its standard deviation (n \u2212 1)."}]},"reference_path":{"calls":[{"args":{"columns":["y"],"dataset":"d"},"tool":"data.describe"}],"needs":[],"provenance":"metadata_rule","quotes":{},"reference_datasets":[],"source_id":null},"unscored":{"r1":{"value_as_published":"-0.307304800605679","why":"no tool states a lag-1 autocorrelation (data.describe has none)"}}},"question":"NIST Statistical Reference Datasets, univariate summary statistics, problem Lew: 200 deflections of a steel-concrete beam while subjected to periodic pressure, measured at NIST. NIST uses this data set to test the accuracy of summary statistics calculations. Dataset d holds the 200 observations in column y. Compute the sample mean of y and the sample standard deviation of y (denominator n \u2212 1).","requires":[],"runner":null,"sources":["nist_univariate.lew.mean","nist_univariate.lew.sd"],"split":"public","suite":"nist_univariate","tags":["nist","certified","univariate","lower","fast","analyst"],"target":"agent","tool":null,"truth":"NIST StRD Lew certified values (500-digit arithmetic), read from the certified block (lines 41-43) of the file itl.nist.gov serves (sha256 081b231f686d\u2026 CRLF, 53cdc7d066ed\u2026 LF); fetched from Internet Archive Wayback Machine, raw snapshot (id_) 20010211025406; lower difficulty, n=200."}