Discrete Survival Time Models: An Application on Marriage Duration

Year 2018, , 377 - 394, 31.12.2018

Hilal Ölmez Hosta Nihal Ata Tutkun

https://doi.org/10.17093/alphanumeric.323904

Abstract

In survival analysis which is used in the social and physical sciences, it is usually assumed that the observed process is continuous. Since this assumption is not appropriate for most of the survival time data structure, survival times are measured wrongly and unreliable results are obtained for the discrete survival time data. Continuous time survival models used for the time data have represented the structure of data in the studies regarding health sciences. The usage of the discrete time survival models in social sciences is more common since the structure of the studied data is more appropriate for the discrete time models.


In this study, discrete time survival models are examined theoretically and were applied to “Research on Domestic Violence against Women in Turkey, 2008” data received from Turkish Statistical Institute. In order to examine the factor effecting the duration of marriage, discrete time survival models have been used and achieved results have been interpreted.

Keywords

Cox regression, Discrete time survival model, Logit model, Non-proportional hazards

Kesikli Yaşam Süresi Modelleri: Evlilik Süreleri Üzerine Bir Uygulama

Abstract

Fen ve sosyal bilimlerde kullanılabilen yaşam modellerinde genellikle ilgilenilen sürecin sürekli olduğu varsayılmaktadır. Ancak böyle bir varsayım bazı yaşam verilerinin yapısına uygun olmadığından yaşam süreleri hatalı ölçülmekte ve kesikli yaşam süresi verileri için güvenilir olmayan sonuçlar elde edilmektedir. Sürekli veriler için kullanılan sürekli yaşam modelleri, sağlık bilimlerinde yer alan uygulamalardaki verilerin yapısını yansıtabilir. Fakat kesikli zaman verilerinin en çok kullanıldığı sosyal bilimler alanında, mevcut verilerin yapısı kesikli modellere daha uygun olduğu için özellikle bu alanda kesikli yaşam süresi modellerinin kullanımı daha yaygındır.

Bu çalışmada, kesikli yaşam süresi modelleri teorik açıdan incelenmiş ve Türkiye İstatistik Kurumu’ndan alınan “Türkiye'de Kadına Yönelik Aile İçi Şiddet Araştırması, 2008” verisine uygulanmıştır. Araştırmada yer alan kadınların evli kalma sürelerine etki eden faktörlerin incelenmesinde kesikli yaşam süresi modelleri kullanılmış ve sonuçlar yorumlanmıştır.

Keywords

Cox regresyon, Kesikli yaşam süresi modelleri, Logit model, Orantısız tehlikeler

References

• [1] Bergstrom, R., Edin, P-A, 1992, Time aggregation and the distributional shape of unemployment duration, Journal of Applied Econometrics, 7, 5-30.
• [2] Blossfeld, H., P., Mills, M., 2001, A Causal Approach to Interrelated Family Events: A Cross-national Comparison of Cohabitation, Nonmarital Conception, and Marriage, Special Issue on Longitudinal Methodology, Canadian Studies in Population, 28(2), 409- 437.
• [3] Box-Steffensmeier, J., Jones, B., 1997, Time Is of the Essence: Event History Models in Political Science, American Journal of Political Science, 41, 1414-1461.
• [4] Box-Steffensmeier, M., J., Jones, S. B., 2004, Event History Modelling, Cambridge Universtiy Press.
• [5] Collett, D., 1994, Modelling Survival Data in Medical Research, London, Chapman&Hall.
• [6] Cox, D.R., 1972, Regression models and life-tables, Journal of the Royal Statistical Society,Series B, 34, 187-220.
• [7] Crowley, J., Hu, M., 1977, Covariance Analysis of Heart Transplant Survival Data, Journal of the American Statistical Association, 72, 27–36.
• [8] Eleuteri, A., Aung, M.S.H., Taktak, A.F.G., Damato, B., Lisboa, P.J.G., 2007, Continuous and discrete time survival analysis: neural network approaches, Engineering in Medicine and Biology Society, 5420-5423.
• [9] Ergöçmen B., Üner S., Yiğit E., 2009, Türkiye’de Kadına Yönelik Şiddet, Ankara.
• [10] García-Moreno, C., Jansen, H. A. F. M., Ellsberg, M., Heise, L., Watts, C, 2005, WHO multi-country study on women's health and domestic violence against women: initial results on prevalance, health outcomes and women's responses, World Health Organisation.
• [11] Geskus, R.B., 2000, On the inclusion of prevalent cases in HIV/AIDS natural history studies through a marker-based estimate of time since seroconversion, Statistics in Medicine, 19, 1753–1769.
• [12] Hannan, M., Carroll, G.R., 1981, Dynamics of formal political structure, Sociological Rev, 46, 19-35.
• [13] Hess, W., Persson, M., Rubenbauer, S., Gertheiss, J., 2011, The Varying Effects of Distance on The Survival of Trade Flows, paper presented at European Trade Study Group (ETSG) 13th Annual Conference, Copenhagen, Denmark.
• [14] Jenkins, S., 2005, Survival Analysis, Institute for Social and Economic Research, University of Essex, Colchester, UK.
• [15] Kalbfleisch, JD, Prentice, RL., 1980, The Statistical Analysis of Failure Time Data, New York , Wiley.
• [16] Mills, M., Johnston, A. D., DiPrete, T. A., 2006, Globalization and Men’s Job Mobility in the United States, Uncertainty and Men’s Careers: An International Comparison, 328–62.
• [17] Ngandu, N.H., 1997, An Emprical Comparision of Statistical Tests For Assessing the Proportional Hazards Assumption of Cox's Model, Statistics in Medicine.,16, 611-626.
• [18] Olzak, S., 1989, Analysis of Events in the Study of Collective Action, Annual Review of Sociology, 15, 119–41.
• [19] Petersen, T, Time-aggregation bias in continuous-time hazard-rate models, Sociological Methodology 1991, Blackwell, Cambridge MA, 1991.
• [20] Petersen, T., Koput K.W., 1992,Time-aggregation hazard-rate models with covariates, Sociological Methods and Research, 21, 2551.
• [21] Pope, C. A., Thun, M., Namboodiri, M., Dockery, D., Evans, J., Speizer, F., and Heath, C., 1995, Particulate air pollution as a predictor of mortality in a prospective study of U.S. adults, American Journal Respiratory Critical Care Medicine, 151, 669–674.
• [22] Smith, T., Smith, B., 1972, Survival Analysis And The Application Of Cox's Proportional Hazards Modeling Using SAS, Department of Defense Center for Deployment Health Research, Naval Health Research Center, San Diego, CA.
• [23] Sueyoshi, G.T., Edin, P-A, 1995, A class of binary response models for grouped duration data, Journal of Applied Econometrics, 10, 411-43.
• [24] Türkiye İstatistik Kurumu (TÜİK), 2008, Türkiye'de Kadına Yönelik Aile İçi Şiddet Araştırması.
• [25] Usui, C., 1994, Welfare State Development in a World System Context: Event History Analysis of First Social Insurance Legislation, Cambridge University Press, 254-77.
• [26] Xie, H., McHugo, G., Sengupta, A., Drake, R. 2003, Using discrete-time analysis to examine patterns of remission from substance use disorder among persons with severe mental illness, Mental Health Services Research, 5:55-64.
• [27] Yang, C.C., 2004, Bayesian Discrete Time Survival Analysis of Multivariate Reoccurrable Events: Surviving Early Depressive Moods, Journal of Research on Measurement & Statistics, 12, 1-18.