XML Persian Abstract Print


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

Ghorbani Gholiabad S, Sadeghifar M, Ghorbani Gholiabad R, Hamidi O. Forecasting Frequency of Delivery using Poisson Hidden Markov Models . irje. 2018; 1111
URL: http://irje.tums.ac.ir/article-1-5801-en.html
1- Department of Biostatistics & Epidemiology, School of Public Health, Hamadan University of Medical Sciences, Hamadan, Iran
2- Department of Statistics, Faculty of Basic Sciences, Bu-Ali Sina University, Hamadan, Iran , Sadeghifar@basu.ac.ir
3- MS of Statistics, Hakim Jorjani Hospital, Gorgan, Iran
4- Department of Science, Hamadan University of Technology, Hamadan, Iran
Abstract:   (1122 Views)
Background & Objectives: Delivery and care of mothers is one of the most important services at health systems which efforts to women's health as one of the health priorities.so this study aimed to forecast number of delivery and the use of all facilities for better services to patients was conducted.
Methods: The data used in this study was the number of deliveries per month in Hakim Jorjani hospital in Gorgan during the years 2010 to 2016.Due to the over-dispersion in the data and non-compliance of a Poisson distribution and also serial correlation between the observations, Poisson hidden Markov model was used to predict the frequency of monthly deliveries. Estimating model parameters with maximum likelihood method and Expectation Maximization algorithm is done.
Results: The performed models and their Comparisons using Akaike's information criterion revealed the frequency of delivery in different months in the hospital follow from a Poisson hidden Markov models with three hidden states, the mean Poisson distribution in each component is 193.74, 236.05 and 272.61 labor, respectively.
Conclusion : The results of this study showed that government’s encouraging policies has had short-term and limited results on increasing fertility and that has little effect on the results of the two-year forecast.
     
Type of Study: Research | Subject: General
Received: 2017/11/12 | Accepted: 2017/11/12 | Published: 2017/11/12

Add your comments about this article : Your username or Email:
Write the security code in the box

Send email to the article author


© 2017 All Rights Reserved | Iranian Journal of Epidemiology

Designed & Developed by : Yektaweb