Discussion: View Thread

Just a reminder about the two back-to-back PDWs on Bayesian Methods at the upcoming Academy of Management Conference in Boston, MA. No pre-registration is required, and we look forward to having you along to discuss exciting advents in the area of Bayesian Methods. The details for the two PDWs are as follows:

PDW #1 Title: Why We All Should Be Bayesians!

Time: Saturday, August 4, 2012 at 10:15 AM – 12:15 PM

Location: Westin Copley, Room: Great Republic

Presenters: David Krackhardt (Carnegie Mellon University), William H. Starbuck (University of Oregon), Michael J. Zyphur (University of Melbourne), Andreas Schwab (Iowa State University)

Abstract:

This workshop introduces management researchers to the opportunities of Bayesian statistics for empirical research in the management sciences. We will outline the fundamental features of the Bayesian method without delving into the mathematical details. Instead, we will first outline the conceptual differences and potential advantages of a Bayesian approach compared to traditional statistical analyses involving null-hypothesis significance tests (NHSTs). We will then show examples from empirical management research that illustrates Bayesian data analysis. Finally, we will discuss why in spite of strong arguments supporting the use of Bayesian statistics, the field of management research has been very reluctant considering Bayesian analysis as an alternative. The purpose of this workshop is to convince participants of the potential opportunities Bayesian methods can provide and to encourage organizational researchers to apply these methods in future research.

PDW #2 Title: Bayesian and Frequentist Research Methods: Theory, History, Estimation, Application, and Integration

Time: Saturday, August 4, 2012 at 12:45 AM – 2:45 PM

Location: Westin Copley, Room: St. George C & D

Presenters: Michael J. Zyphur (University of Melbourne), Dean Pierides (University of Melbourne)

Abstract:

This workshop introduces a Bayesian theory of probability for inductive inference in organization and management science. Currently, a frequentist theory dominates. The difference between the two theories is that Bayesian probability references a degree of belief in a proposition or state of affairs, while frequentist probability references the relative frequency of an observation or event in an infinite series of observations or events. The foundations of Bayesian and frequentist probability will be described, as well as their histories, methods of estimation, targets for application, and how they can both be used to greatly expand the potential for rigorous and relevant research. Estimation will be conducted in the popular statistics program Mplus. Program code, datasets, and interpretations of results will be incorporated into the workshop, including decision-theoretic foundations of making inductive inferences using different theories of probability.

Dear Colleagues,

As a follow up to the message from Andreas below, those of you looking for an accessible source that provides an overview of Bayesian methods and what they have to offer may be interested in the following article to be published in Organizational Research Methods:

Kruschke, J. K., Aguinis, H., & Joo, H. (in press). The time has come: Bayesian methods for data analysis in the organizational sciences. Organizational Research Methods.

The article's Abstract is below. Also, a pre-print of this article is available at http://mypage.iu.edu/~haguinis/pubs.html

All the best,

--Herman.

*****************************************************

Herman Aguinis, Ph.D.

Dean's Research Professor and

Professor of Organizational Behavior and Human Resources

Founding Director, Institute for Global Organizational Effectiveness

Department of Management and Entrepreneurship

Kelley School of Business, Indiana University

http://mypage.iu.edu/~haguinis/

****************************************************

The Time Has Come: Bayesian Methods for Data Analysis in the Organizational Sciences

The use of Bayesian methods for data analysis is creating a revolution in fields ranging from genetics to marketing. Yet, results of our literature review including more than 10,000 articles published in 15 journals from January 2001 and December 2010 indicate that Bayesian approaches are essentially absent from the organizational sciences. Our article introduces organizational science researchers to Bayesian methods and describes why and how they should be used. We use multiple linear regression as the framework to offer a step-by-step demonstration, including the use of software, regarding how to implement Bayesian methods. We explain and illustrate how to determine the prior distribution, how to compute the posterior distribution, how to possibly accept the null value, and how to produce a write-up describing the entire Bayesian process including graphs, results, and their interpretation. We also offer a summary of the advantages of using Bayesian analysis and examples of how specific published research based on frequentist analysis-based approaches failed to benefit from the advantages offered by a Bayesian approach and how using Bayesian analyses would have led to richer and, in some cases, different substantive conclusions. We hope that our article will serve as a catalyst for the adoption of Bayesian methods in organizational science research.