{"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.numacc2.mean","table":"columns","tool":"data.describe","value":1.2,"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.numacc2.sd","table":"columns","tool":"data.describe","value":0.1,"weight":1.0,"where":{"column":"y"}}],"datasets":{"d":{"columns":["y"],"description":"NIST StRD NumAcc2: 1001 observations of y, one per row","file_sha256":"5be29522dfbe299541f0ec98ec1c22a51a5587bf06561ba21a92c209fb7ef0f9","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":"5be29522dfbe299541f0ec98ec1c22a51a5587bf06561ba21a92c209fb7ef0f9","transforms":[],"url":"https://raw.githubusercontent.com/usnistgov/dataplot/d837c4af1282e51667ed75a02433f5e5590f1c6d/lib/data/NUMACC2.DAT"}},"difficulty":"M","id":"nist_univariate.numacc2.agent","level":"T2","meta":{"cluster":"5be29522dfbe299541f0ec98ec1c22a51a5587bf06561ba21a92c209fb7ef0f9","difficulty":"average","double_frame_lre":{"mean":15.0,"sd":15.0},"expected_tool":"data.describe","gold_kind":"derived","min_lre":9.0,"native_id":"NumAcc2","problem":"NumAcc2","question_omits":["r(1), the lag-1 autocorrelation NIST also certifies: no tool states it","the values the NIST description states by construction"],"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":"-0.999 (exact)","why":"no tool states a lag-1 autocorrelation (data.describe has none)"}}},"question":"NIST Statistical Reference Datasets, univariate summary statistics, problem NumAcc2: 1001 constructed values: 2-digit floating-point numbers that differ only in the last decimal place. NIST uses this data set to test the accuracy of summary statistics calculations. Dataset d holds the 1001 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.numacc2.mean","nist_univariate.numacc2.sd"],"split":"public","suite":"nist_univariate","tags":["nist","certified","univariate","average","fast","analyst"],"target":"agent","tool":null,"truth":"NIST StRD NumAcc2 certified values (500-digit arithmetic), read from the certified block (lines 41-43) of the file itl.nist.gov serves (sha256 5be29522dfbe\u2026 CRLF, 2f9bc7f02a4e\u2026 LF); fetched from usnistgov/dataplot@d837c4af1282e51667ed75a02433f5e5590f1c6d:lib/data/NUMACC2.DAT; average difficulty, n=1001."}