Binary Response and Logistic Regression in Recent Accounting Research Publications: A Methodological Note

Posted: 28 Jun 2010

See all articles by Wenxia Ge

Wenxia Ge

University of Ottawa

G. A. Whitmore

McGill University

Multiple version iconThere are 2 versions of this paper

Date Written: May 1, 2009

Abstract

We review 31 articles in leading accounting journals that performed a logistic regression analysis for a binary dependent variable. Our review shows that many of these articles have ambiguities and errors in the presentation of the logistic regression model. We explain that incorrect presentations of the model, even in conjunction with a correct analysis, may lead to a serious misinterpretation of research findings. Two articles are critiqued to demonstrate the reporting problems. Our note is a call for improvement in model presentation and related statistical analysis in the accounting field.

Keywords: Binary response variable, Discriminant analysis, Logistic regression, Accounting research

JEL Classification: M40, M49

Suggested Citation

Ge, Wenxia and Whitmore, G. A., Binary Response and Logistic Regression in Recent Accounting Research Publications: A Methodological Note (May 1, 2009). Review of Quantitative Finance and Accounting, Vol. 34, No. 1, pp. 81-93, 2010, Available at SSRN: https://ssrn.com/abstract=1397730

Wenxia Ge (Contact Author)

University of Ottawa ( email )

55 Laurier Avenue East
Ottawa, Ontario K1N 6N5
Canada

G. A. Whitmore

McGill University ( email )

1001 Sherbrooke St. West
Montreal, Quebec H3A 1G5
Canada
514-398-4049 (Phone)
514-398-3876 (Fax)

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
1,451
PlumX Metrics