Bayes factors vs. P-values

Abstract The use of p-values for hypothesis testing has always been the norm in the tourism literature. This paper proposes the use of Bayes factors as an attractive alternative for hypothesis testing. As the Bayes factor is based on the Bayesian approach, which relies solely on the observed sample to provide direct probability statements about the parameters of interest, it is more suited for the purpose of hypothesis testing. Importantly, in this paper we show that the Bayes factor has nicer properties than the p-value, a fact that should be of interest irrespective of whether the user is Bayesian or not. We discuss in more details the advantages of Bayes factors, and provide several interesting recommendations throughout the paper.

[1]  Albert Vexler,et al.  Data-Driven Confidence Interval Estimation Incorporating Prior Information with an Adjustment for Skewed Data , 2016 .

[2]  Hal S Stern,et al.  A Test by Any Other Name: P Values, Bayes Factors, and Statistical Inference , 2016, Multivariate behavioral research.

[3]  Efthymios G. Tsionas,et al.  Incorporating destination quality into the measurement of tourism performance: A Bayesian approach , 2015 .

[4]  M. Zyphur,et al.  Bayesian Estimation and Inference , 2015 .

[5]  N. Lazar,et al.  The ASA Statement on p-Values: Context, Process, and Purpose , 2016 .

[6]  S. Goodman.  Toward Evidence-Based Medical Statistics. 1: The P Value Fallacy , 1999, Annals of Internal Medicine.

[7]  L. Wasserman,et al.  Computing Bayes Factors Using a Generalization of the Savage-Dickey Density Ratio , 1995 .

[8]  Ward Edwards,et al.  Bayesian statistical inference for psychological research. , 1963 .

[9]  J. Berger,et al.  The Intrinsic Bayes Factor for Model Selection and Prediction , 1996 .

[10]  L. Wasserman,et al.  Computing Bayes Factors by Combining Simulation and Asymptotic Approximations , 1997 .

[11]  Peter E. Rossi,et al.  Bayesian Statistics and Marketing , 2005 .

[12]  M. J. Bayarri,et al.  Calibration of ρ Values for Testing Precise Null Hypotheses , 2001 .

[13]  S. Goodman.  Introduction to Bayesian methods I: measuring the strength of evidence , 2005, Clinical trials.

[14]  Y. Ritov,et al.  Response to the ASA’s Statement on p-Values: Context, Process, and Purpose , 2017 .

[15]  S. Goodman,et al.  A comment on replication, p-values and evidence. , 1992, Statistics in medicine.

[16]  G. Cumming.  Understanding the New Statistics: Effect Sizes, Confidence Intervals, and Meta-Analysis , 2011 .

[17]  V. Johnson.  Revised standards for statistical evidence , 2013, Proceedings of the National Academy of Sciences.

[18]  A. Mattila,et al.  Advertising spending, firm performance, and the moderating impact of CSR , 2017 .

[19]  Zoltan Dienes,et al.  Using Bayes to get the most out of non-significant results , 2014, Front. Psychol..

[20]  Frederick L. Oswald,et al.  Bayesian Probability and Statistics in Management Research , 2013 .

[21]  Donald A. Berry,et al.  Statistics: A Bayesian Perspective , 1995 .

[22]  T. Louis.  Introduction to Bayesian methods II: fundamental concepts , 2005, Clinical trials.

[23]  H. Jeffreys,et al.  The Theory of Probability , 1896 .

[24]  Peter Congdon.  Bayesian statistical modelling , 2002 .

[25]  Efthymios G. Tsionas,et al.  Short-run and long-run performance of international tourism: evidence from Bayesian dynamic models. , 2014 .

[26]  E. Wagenmakers,et al.  A Bayesian Perspective on Hypothesis Testing , 2006, Psychological science.

[27]  Donald A Berry,et al.  Introduction to Bayesian methods III: use and interpretation of Bayesian tools in design and analysis , 2005, Clinical trials.

[28]  M. Schervish,et al.  Bayes Factors: What They are and What They are Not , 1999 .

[29]  A. Tasci,et al.  Large sample size, significance level, and the effect size: Solutions to perils of using big data for academic research , 2017 .

[30]  S. Goodman.  A dirty dozen: twelve p-value misconceptions. , 2008, Seminars in hematology.

[31]  Jeffrey N. Rouder,et al.  Bayesian t tests for accepting and rejecting the null hypothesis , 2009, Psychonomic bulletin & review.