UUM Repository | Universiti Utara Malaysian Institutional Repository
FAQs | Feedback | Search Tips | Sitemap

Projection of postgraduate students flow with a smoothing matrix transition diagram of Markov chain


Rahim, Rahela and Ibrahim, Haslinda and Adnan, Farah Adibah (2013) Projection of postgraduate students flow with a smoothing matrix transition diagram of Markov chain. In: 20th National Symposium on Mathematical Sciences, 18–20 December 2012, Palm Garden Hotel, Putrajaya, Malaysia.

[img] PDF
Restricted to Repository staff only

Download (188kB) | Request a copy

Abstract

This paper presents a case study of modeling postgraduate students flow at the College of Art and Sciences, Universiti Utara Malaysia. First, full time postgraduate students and the semester they were in are identified. Then administrative data were used to estimate the transitions between these semesters for the year 2001-2005 periods. Markov chain model is developed to calculate the -5 and -10 years projection of postgraduate students flow at the college. The optimization question addressed in this study is 'Which transitions would sustain the desired structure in the dynamic situation such as trend towards graduation?' The smoothed transition probabilities are proposed to estimate the transition probabilities matrix of 16 × 16.The results shows that using smoothed transition probabilities, the projection number of postgraduate students enrolled in the respective semesters are closer to actual than using the conventional steady states transition probabilities

Item Type: Conference or Workshop Item (Paper)
Additional Information: AIP Conference Proceedings ISSN: 0094-243X
Uncontrolled Keywords: markov chain, smoothing technique, students flow
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: College of Arts and Sciences
Depositing User: Dr. Rahela Abdul Rahim
Date Deposited: 23 Oct 2014 03:21
Last Modified: 23 Oct 2014 03:21
URI: http://repo.uum.edu.my/id/eprint/12347

Actions (login required)

View Item View Item