Reporting dichotomous data using Logistic Regression in Medical Research: The scenario in developing countries

Brijesh Sathian


Logistic regression is one of the powerful analytical techniques for use when the outcome variable is dichotomous and the coefficients derived from logistic regression can be interpreted as odds ratio. The analysis under logistic regression gives the β coefficient along with the odds ratio and 95% confidence interval for odds ratio. Since the β coefficients are the natural logarithm of the risk, we have to exponentiate them to get the estimate of risk (odds ratio). Currently, the most widely used statistical methodology for reporting dichotomous data in developed countries is logistic regression analysis. But in developing countries, several research studies with dichotomous data are reported using percentages or cross tabulation method because of the ignorance of the application and knowledge of this methodology among the authors, readers, reviewers and editors.  This trend in developing countries should be changed through the use of appropriate statistical methods with the help of professional data analysts, otherwise research cannot investigate vital findings.

Nepal Journal of Epidemiology 2011;1(4):111-113


Logistic Regression; Sample size determination; Odds Ratio

Full Text:



Copyright (c)

Indexed in PubMed, PubMed Central, the Emerging Sources Citation Index (Thomson Reuters), Ulrich's International Periodicals Directory (UPD), Google Scholar, Academic Journals Database, Biomedical Research Directory (, BASE, NewJour, INCLEN Online Library, WorldCat,,'Elektronische Zeitschriftenbibliothek EZB (Electronic Journals Library), SCOLAR, Electronic Journals and Periodicals [Psychology], HINARI, EMBASE and SafetyLit.