Significance Tests in Climate Science

被引：27
作者：
Ambaum, Maarten H. P. [1 ]
机构：
[1] Univ Reading, Dept Meteorol, Reading RG6 6BB, Berks, England
来源：
JOURNAL OF CLIMATE | 2010年 / 23卷 / 22期
关键词：
Bayesian methods; Climatology; Statistical techniques;
D O I：
10.1175/2010JCLI3746.1
中图分类号：
P4 [大气科学（气象学）];
学科分类号：
0706 ; 070601 ;
摘要：
A large fraction of papers in the climate literature includes erroneous uses of significance tests. A Bayesian analysis is presented to highlight the meaning of significance tests and why typical misuse occurs. The significance statistic is not a quantitative measure of how confident one can be of the "reality" of a given result. It is concluded that a significance test very rarely provides useful quantitative information.
引用
收藏
页码：5927 / 5932
页数：6
相关论文
共 13 条
  • [1] [Anonymous], 1961, The Algebra of Probable Inference
  • [2] [Anonymous], 2003, Probability Theory
  • [3] Significance tests harm progress in forecasting
    Armstrong, J. Scott
    [J]. INTERNATIONAL JOURNAL OF FORECASTING, 2007, 23 (02) : 321 - 327
  • [4] COHEN J, 1994, AM PSYCHOL, V49, P997, DOI 10.1037/0003-066X.50.12.1103
  • [5] Needed: A ban on the significance test
    Hunter, JE
    [J]. PSYCHOLOGICAL SCIENCE, 1997, 8 (01) : 3 - 7
  • [6] PRIOR PROBABILITIES
    JAYNES, ET
    [J]. IEEE TRANSACTIONS ON SYSTEMS SCIENCE AND CYBERNETICS, 1968, SSC4 (03): : 227 - &
  • [7] Jolliffe I.T., 2004, Weather, V59, P77, DOI [10.1256/wea.132. 03, DOI 10.1256/WEA.132.03]
  • [8] Nicholls N, 2001, B AM METEOROL SOC, V82, P981, DOI 10.1175/1520-0477(2001)082<0981:CAATIO>2.3.CO
  • [9] 2
  • [10] Ryle G., 1949, The concept of mind, DOI 10.4324/9780203875858
12