Beata Jackowska

(Polish) PDF


The aims of this paper include the identification of predictors of death risk and the examination of interaction effects between them. In this study, a logistic regression model is used to estimate death probability at old age (above 60) in the Pomorskie Voivodship in 2009. The following risk factors of death are considered: age, gender and place of residence (urban/rural areas). In the model, age is treated both as a continuous variable and as a categorical variable. The paper presents an analysis of interaction effects between predictors with the use of product terms in the logistic regression model. The emphasis is on the interpretation of the coefficients of the interactive logistic model. The study includes cases of interactions between qualitative predictors, between qualitative and quantitative predictors, and between quantitative predictors. It appears that the interaction between gender and age is statistically significant.


logistic regression, interaction effect, death probability


[1] Agresti A., [2002], Categorical Data Analysis, John Wiley & Sons, New Jersey.

[2] Christensen R. Ch., [1997], Log-linear models and logistic regression, Springer, New York.

[3] Gruszczyński M., [2010], Modele zmiennych jakościowych dwumianowych, W: Mikroekonometria. Modele i metody analizy danych indywidualnych, pod red. Gruszczyński M., Wolters Kluwer Polska, Warszawa.

[4] Harrell F., [2001], Regression Modeling Strategies with Applications to Linear Models, Logistic Regression, and Survival Analysis, Springer-Verlag, New York.

[5] Hosmer D., Lemeshow S., [2000], Applied Logistic Regression, John Wiley & Sons, New Jersey.

[6] Jaccard J., [2001], Interaction Effects in Logistic Regression, Sage University Papers, Series: „Quantitative Applications in the Social Sciences”, 07-135, Thousand Oaks.

[7] Jong de P., Heller G. Z., [2008], Generalized Linear Models for Insurance Data, Cambridge University Press, Cambridge.

[8] Maddala G. S., [1983], Limited-dependent and qualitative variables in econometrics, Cambridge University Press, Cambridge.

[9] Mazurek E., [2000], Model logitowy, W: Metody oceny i porządkowania ryzyka w ubezpieczeniach życiowych, pod red. Ostasiewicz S., Wydawnictwo Akademii Ekonomicznej we Wrocławiu, Wrocław.

[10] McCullagh P., Nelder J. A., [1989], Generalized Linear Models, Chapman & Hall, London.

[11] Tabeau E., Willekens F., van Poppel F., [2002], Parameterization as a tool in analyzing age, period and cohort effects on mortality: A case study of the Netherlands, W: The Life Table. Modelling Survival and Death, pod red. Wunsch G., Mouchart M., Duchene J., Kluwer Academic Publishers, Dordrecht.

[12] Trwanie życia w 2009 r., [2010], Główny Urząd Statystyczny, Warszawa.

Back to top
© 2019–2022 Copyright by Statistics Poland, some rights reserved. Creative Commons Attribution-ShareAlike 4.0 International Public License (CC BY-SA 4.0) Creative Commons — Attribution-ShareAlike 4.0 International — CC BY-SA 4.0