Volume 29, Issue 1 (1-2015)                   Med J Islam Repub Iran 2015 | Back to browse issues page

XML Print


Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Salehi M, Roudbari M. Zero inflated Poisson and negative binomial regression models: application in education. Med J Islam Repub Iran. 2015; 29 (1) :1177-1183
URL: http://mjiri.iums.ac.ir/article-1-3328-en.html
Antimicrobial Resistance Research Center, Rasoul-e-Akram Hospital, Department of Biostatistics, School of Public Health, Iran University of Medical Sciences, Tehran, Iran. , mroudbari@yahoo.co.uk
Abstract:   (2103 Views)

Background: The number of failed courses and semesters in students are indicatorsof their performance. These amounts have zero inflated (ZI) distributions. Using ZI Poisson and negative binomial distributions we can model these count data to find the associated factors and estimate the parameters. This study aims at to investigate the important factors related to the educational performance of students.

Methods: This cross-sectional study performed in 2008-2009 at Iran University of Medical Sciences (IUMS) with a population of almost 6000 students, 670 students selected using stratified random sampling. The educational and demographical data were collected using the University records. The study design was approved at IUMS and the students’ data kept confidential. The descriptive statistics and ZI Poisson and negative binomial regressions were used to analyze the data. The data were analyzed using STATA.

Results: In the number of failed semesters, Poisson and negative binomial distributions with ZI, students’ total average and quota system had the most roles. For the number of failed courses, total average, and being in undergraduate or master levels had the most effect in both models.

Conclusion: In all models the total average have the most effect on the number of failed courses or semesters. The next important factor is quota system in failed semester and undergraduate and master levels in failed courses. Therefore, average has an important inverse effect on the numbers of failed courses and semester.

Full-Text [PDF 510 kb]   (1057 Downloads)    

Add your comments about this article : Your username or Email:
CAPTCHA code

Send email to the article author