Confidence intervals are a more useful complement to nonsignificant tests than are power calculations

被引：204

作者：

Colegrave, N

Ruxton, GD

机构：

[1] Univ Edinburgh, Inst Cell Anim & Populat Biol, Ashworth Lab, Edinburgh EH9 3JT, Midlothian, Scotland

[2] Univ Glasgow, Div Environm & Evolutionary Biol IBLS, Glasgow G12 8QQ, Lanark, Scotland

来源：

关键词：

D O I：

10.1093/beheco/14.3.446

中图分类号：

B84 [心理学]; C [社会科学总论]; Q98 [人类学];

学科分类号：

03 ; 0303 ; 030303 ; 04 ; 0402 ;

摘要：

[No abstract available]

引用

页码：446 / U4

页数：2

共 5 条

[1] Cohen J., 1998, Statistical Power Analysis for the Behavioral Sciences, V2nd
[2] The abuse of power: The pervasive fallacy of power calculations for data analysis
Hoenig, JM
Heisey, DM
[J]. AMERICAN STATISTICIAN, 2001, 55 (01) : 19 - 24
[3] The insignificance of statistical significance testing
Johnson, DH
[J]. JOURNAL OF WILDLIFE MANAGEMENT, 1999, 63 (03) : 763 - 772
[4] Lipsey M.W., 1990, Design sensitivity: Statistical power for experimental research, V19
[5] A COMPARISON OF THE 2 ONE-SIDED TESTS PROCEDURE AND THE POWER APPROACH FOR ASSESSING THE EQUIVALENCE OF AVERAGE BIOAVAILABILITY
SCHUIRMANN, DJ
[J]. JOURNAL OF PHARMACOKINETICS AND BIOPHARMACEUTICS, 1987, 15 (06): : 657 - 680