THE SEARCH FOR ASTERISKS: COMPROMISED STATISTICAL TESTS AND FLAWED THEORIES

被引：111

作者：

Bettis, Richard A. ^{[1
]}

机构：

[1] Univ N Carolina, Kenan Flager Business Sch, Strategy & Entrepreneurship Dept, Chapel Hill, NC 27599 USA

来源：

STRATEGIC MANAGEMENT JOURNAL | 2012年 / 33卷 / 01期

关键词：

statistical methodology; significance levels; data snooping; theory testing; replication;

D O I：

10.1002/smj.975

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

This paper discusses repeated tests and the resultant reporting of statistical significance when it is actually not present. These errors interact with professional norms such as biases against both replication studies and 'non-results' to undermine the efficacy of our base of empirically tested theory. This raises serious issues for the future of strategic management research. Suggestions are made for dealing with these issues substantively and in terms of professional norms. Copyright (C) 2011 John Wiley & Sons, Ltd.

引用

页码：108 / 113

页数：6

共 12 条

[1]

[Anonymous], 2009, Cambridge University Press, DOI DOI 10.1017/CBO9780511815867

[2]

Berk RA, 2004, Regression Analysis: A Constructive Critique, V11

[3]

Blettner D, 2012, STRATEGIC M IN PRESS, V33

[4]

Freedman DH, 2010, ATLANTIC MAGAZIN NOV

[5]

Hand D., 2001, ADAP COMP MACH LEARN

[6]

Hosmer W., 2000, Applied Logistic Regression, VSecond

[7] An Epidemic of False Claims [J].

Ioannidis, John P. A. .

SCIENTIFIC AMERICAN, 2011, 304 (06) :16-16

[8] Contradicted and initially stronger effects in highly cited clinical research [J].

Ioannidis, JPA .

JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2005, 294 (02) :218-228

[9]

Lehrer J., 2010, NEW YORKER 1113

[10] TESTING MANAGEMENT THEORIES: CRITICAL REALIST PHILOSOPHY AND RESEARCH METHODS [J].

Miller, Kent D. ;

Tsang, Eric W. K. .

STRATEGIC MANAGEMENT JOURNAL, 2011, 32 (02) :139-158

← 1 2 →