The Perpetual Student: Modelling Duration of Undergraduate Studies based on Lifetime-type educational data

A Kalamatianou, SI McClean

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

It is important to educational planners to estimate the likelihood and time-scale of graduation of students enrolled on a curriculum. The particular case we are concerned with, emerges when studies are not completed in the prescribed interval of time. Under these circumstances we use a framework of survival analysis applied to lifetime-type educational data to examine the distribution of duration of undergraduate studies for 10,313 students, enrolled in a Greek university during ten consecutive academic years. Non-parametric and parametric survival models have been developed for handling this distribution as well as a modified procedure for testing goodness-of fit of the models. Data censoring was taken into account in the statistical analysis and the problems of thresholding of graduation and of perpetual students are also addressed. We found that the proposed parametric model adequately describes the empirical distribution provided by non-parametric estimation. We also found significant difference between duration of studies of men and women students. The proposed methodology could be useful to analyse data from any other type and level of education or general lifetime data with similar characteristics.
LanguageEnglish
Pages311-330
JournalLifetime Data Analysis
Volume9
Issue number4
DOIs
Publication statusPublished - 1 Dec 2003

Fingerprint

duration of studies
student
level of education
statistical analysis
curriculum
university
methodology
time

Cite this

@article{5744898ccc864f1296c5709c41ba1ec3,
title = "The Perpetual Student: Modelling Duration of Undergraduate Studies based on Lifetime-type educational data",
abstract = "It is important to educational planners to estimate the likelihood and time-scale of graduation of students enrolled on a curriculum. The particular case we are concerned with, emerges when studies are not completed in the prescribed interval of time. Under these circumstances we use a framework of survival analysis applied to lifetime-type educational data to examine the distribution of duration of undergraduate studies for 10,313 students, enrolled in a Greek university during ten consecutive academic years. Non-parametric and parametric survival models have been developed for handling this distribution as well as a modified procedure for testing goodness-of fit of the models. Data censoring was taken into account in the statistical analysis and the problems of thresholding of graduation and of perpetual students are also addressed. We found that the proposed parametric model adequately describes the empirical distribution provided by non-parametric estimation. We also found significant difference between duration of studies of men and women students. The proposed methodology could be useful to analyse data from any other type and level of education or general lifetime data with similar characteristics.",
author = "A Kalamatianou and SI McClean",
year = "2003",
month = "12",
day = "1",
doi = "10.1023/B:LIDA.0000012419.98989.d4",
language = "English",
volume = "9",
pages = "311--330",
journal = "Lifetime Data Analysis",
issn = "1380-7870",
number = "4",

}

The Perpetual Student: Modelling Duration of Undergraduate Studies based on Lifetime-type educational data. / Kalamatianou, A; McClean, SI.

In: Lifetime Data Analysis, Vol. 9, No. 4, 01.12.2003, p. 311-330.

Research output: Contribution to journalArticle

TY - JOUR

T1 - The Perpetual Student: Modelling Duration of Undergraduate Studies based on Lifetime-type educational data

AU - Kalamatianou, A

AU - McClean, SI

PY - 2003/12/1

Y1 - 2003/12/1

N2 - It is important to educational planners to estimate the likelihood and time-scale of graduation of students enrolled on a curriculum. The particular case we are concerned with, emerges when studies are not completed in the prescribed interval of time. Under these circumstances we use a framework of survival analysis applied to lifetime-type educational data to examine the distribution of duration of undergraduate studies for 10,313 students, enrolled in a Greek university during ten consecutive academic years. Non-parametric and parametric survival models have been developed for handling this distribution as well as a modified procedure for testing goodness-of fit of the models. Data censoring was taken into account in the statistical analysis and the problems of thresholding of graduation and of perpetual students are also addressed. We found that the proposed parametric model adequately describes the empirical distribution provided by non-parametric estimation. We also found significant difference between duration of studies of men and women students. The proposed methodology could be useful to analyse data from any other type and level of education or general lifetime data with similar characteristics.

AB - It is important to educational planners to estimate the likelihood and time-scale of graduation of students enrolled on a curriculum. The particular case we are concerned with, emerges when studies are not completed in the prescribed interval of time. Under these circumstances we use a framework of survival analysis applied to lifetime-type educational data to examine the distribution of duration of undergraduate studies for 10,313 students, enrolled in a Greek university during ten consecutive academic years. Non-parametric and parametric survival models have been developed for handling this distribution as well as a modified procedure for testing goodness-of fit of the models. Data censoring was taken into account in the statistical analysis and the problems of thresholding of graduation and of perpetual students are also addressed. We found that the proposed parametric model adequately describes the empirical distribution provided by non-parametric estimation. We also found significant difference between duration of studies of men and women students. The proposed methodology could be useful to analyse data from any other type and level of education or general lifetime data with similar characteristics.

U2 - 10.1023/B:LIDA.0000012419.98989.d4

DO - 10.1023/B:LIDA.0000012419.98989.d4

M3 - Article

VL - 9

SP - 311

EP - 330

JO - Lifetime Data Analysis

T2 - Lifetime Data Analysis

JF - Lifetime Data Analysis

SN - 1380-7870

IS - 4

ER -