Random effects logistic regression model for data envelopment analysis with correlated decision making units

So Young Sohn, H. Choi

Research output: Contribution to journalArticle

7 Citations (Scopus)


This study attempts to exploit information from environmental variables together with data envelopment analysis (DEA) efficiency scores for efficiency predictions of groups with more limited information. Based on DEA efficiency scores, decision-making units (DMUs) are sorted into two sets containing efficient and inefficient units, respectively. Then they are reshuffled into homogeneous groups with respect to environmental factors. We assume that the efficiency of DMUs in such a homogeneous group would be correlated. However, efficiency of different groups would vary. A beta binomial logistic model is proposed to fit such phenomena and is applied to predict the performance of a new group of commercialization projects for given environmental characteristics.

Original languageEnglish
Pages (from-to)552-560
Number of pages9
JournalJournal of the Operational Research Society
Issue number5
Publication statusPublished - 2006 May 1


All Science Journal Classification (ASJC) codes

  • Management of Technology and Innovation
  • Strategy and Management
  • Management Science and Operations Research

Cite this