Quality and Quantity

, Volume 40, Issue 6, pp 935–957 | Cite as

A Geo-Additive Bayesian Discrete-Time Survival Model and its Application to Spatial Analysis of Childhood Mortality in Malawi

  • Ngianga-Bakwin Kandala
  • Gebrenegus GhilagaberEmail author


We describe a flexible geo-additive Bayesian survival model that controls, simultaneously, for spatial dependence and possible nonlinear or time-varying effects of other variables. Inference is fully Bayesian and is based on recently developed Markov Chain Monte Carlo techniques. In illustrating the model we introduce a spatial dimension in modelling under-five mortality among Malawian children using data from Malawi Demographic and Health Survey of 2000. The results show that district-level socioeconomic characteristics are important determinants of childhood mortality. More importantly, a separate spatial process produces district clustering of childhood mortality indicating the importance of spatial effects. The visual nature of the maps presented in this paper highlights relationships that would, otherwise, be overlooked in standard methods.


Bayesian inference discrete-time survival models geo-additive models Markov Chain Monte Carlo (MCMC) Spatial modelling time-varying effects under-five mortality 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Berger U., Fahmeir L. & Klasen S. (2002). Dynamic modelling of child Mortality in developing countries: Application for Zambia. SFB Discussion Paper 299, University of Munich.Google Scholar
  2. Besag, J., York, Y., Mollie, A. 1991Bayesian image restoration with two applications in spatial statisticsAnnual Institute of Statistical Mathematics43159CrossRefGoogle Scholar
  3. Bicego, G. & Ahmad, (1996). Infant and child mortality. Demographic and Health Surveys, Comparative Studies No.20 Macro Int. Inc.Google Scholar
  4. Boerma, J.T., Bicego, G. 1992Preceding birth intervals and child survival: Searching for Pathways of InfluenceStudies in Family Planning23243256CrossRefGoogle Scholar
  5. Bolstad, W.M., Manda, S.O. 2001Investigating child mortality in Malawi using family and community random effects: A Bayesian analysisJournal of the American Statistical Association961219CrossRefGoogle Scholar
  6. Borgoni, R., Billardi, F.C. 2003Bayesian spatial analysis of demographic survey data: An application to contraceptive use at first sexual intercourseDemographic Research836192Google Scholar
  7. Brezger, A., Kneib, T. & Lang, S. (2002). BayesX-Software for Bayesian Inference Based on Markov Chain Monte Carlo Simulation Techniques ( Scholar
  8. Brockerhoff, M. 1990Rural-to-urban migration and child survival in SenegalDemography27601116Google Scholar
  9. Brockerhoff, M. (1993). Child Survival in Big Cities: Are the Poor Disadvantaged? Working Paper 58, New York: The pop. Council, Research Division.Google Scholar
  10. Brockerhoff, M., Derose, L.F. 1996Child survival in East Africa: The impact of preventive health careWorld Development2418411857CrossRefGoogle Scholar
  11. Claeson, M., Bos, E.R., Mawji, T., Pathmanthan, I. 2000Reducing child mortality in India in the new milleniumBulletin of the World Health Organisation7811921199Google Scholar
  12. Cleland, J., Sathar, Z.A. 1984The effect of birth spacing on childhood mortality in PakistanPopulation studies38401418CrossRefGoogle Scholar
  13. Curtis, S.L., Steele, F. 1996Variations in familial neaonatal mortality risks in four countriesJournal of Biosocial Science28141159Google Scholar
  14. DaVanzo, J., Butz, W.P., Habicht, J.P. 1983How biological and behavioural influences on mortality in Malaysia vary during the first year of lifePopulation studies37381402CrossRefGoogle Scholar
  15. Defo, B.K., Khassoum, D. 2002Geography of child mortality clustering within African familiesHealth and Place893117CrossRefGoogle Scholar
  16. Desai, S., Alva, S. 1998Maternal education and child health: Is there a strong causal relationship?Demography357181Google Scholar
  17. Fahrmeir, L., Lang, S. 2001aBayesian Inference for generalized additive mixed models based on markov random field priorsApplied Statistics (JRSS C)50201220CrossRefGoogle Scholar
  18. Fahrmeir, L., Lang, S. 2001bBayesian semiparametric regression analysis of multicategorical time-space dataAnnual Institute of Statistical Mathematics531130CrossRefGoogle Scholar
  19. Gamerman, D. 1997Efficient sampling from the posterior distribution in generalized linear mixed modelsStatistics Computing75768CrossRefGoogle Scholar
  20. Geronimus, A.T., Korenman, S. 1993The socio-economic costs of teenage childbearing: Evidence and interpretationDemography30281290Google Scholar
  21. Ghilagaber, G. (2004). Disentangling Selection and Causality in Assessing the Contribution of Health Inputs to Child Survival: Evidence from East Africa. Research Report 2004:7, Department of Statistics, Stockholm University.Google Scholar
  22. Goldstein, H. (1999). Multilevel statistical models. First Internet Edition. (http://multilevel. Scholar
  23. Guilkey, D., Riphahn, R. 1997The determinants of child mortality in the Philipines: Estimation of structural modelJournal of Development Economics56281305CrossRefGoogle Scholar
  24. Hobart, J., Casella, G. 1996The effect of improper priors on gibbs sampling in hierachical linear mixed modelsJournal of the American Stastiscal Association9114611473CrossRefGoogle Scholar
  25. Kandala, N. -B. (2002). Spatial modelling of socio-economic and demographic determinants of childhood undernutrition and mortality in Africa. Ph.D Thesis, University of Munich, Shaker Verlag.Google Scholar
  26. Knorr-Held, L. 1999Conditional prior proposals in dynamic modelsScandinavian Journal of Statistics26129144CrossRefGoogle Scholar
  27. Knorr-Held, L., Rue, H. 2002On block updating in Markov random field models for disease mappingScandinavian Journal of Statistics29597614CrossRefGoogle Scholar
  28. Koenig, M.A., Phillips, J.F., Campbell, O.M., D’Souza, S. 1990Birth intervals and childhood mortality in rural BangladeshDemography27251265Google Scholar
  29. Lagakos, S.W. 1979General right censoring and its impact on the analysis of survival dataBiometrics35139156CrossRefGoogle Scholar
  30. Langford, I.H., Leyland, A.H., Rabash, J., Goldstein, H. 1999Multilevel modeling of the geographical distributions of diseasesJournal of Royal Statistical Society, Series A (Applied Statistics)48253268CrossRefGoogle Scholar
  31. Macassa, M., Ghilagaber, G., Bernhardt, E., Diderichsen, F., Burström, B. 2003Inequalities in child mortality in Mozambique: Differentials by parental socioeconomic positionSocial Science and Medicine5722552264Google Scholar
  32. Madise, N.J., Diamond, I. 1995Determinants of infant mortality in Malawi: an analysis to control for death clustering within familiesJournal of Biosocial Science2795106CrossRefGoogle Scholar
  33. Madise, N.J., Matthews, Z., Margetts, B. 1999Heterogeneity of child nutritional status between households: A comparison of six sub-saharan African countriesPopulation Studies53331343CrossRefGoogle Scholar
  34. Manda S. O. M., (1998). Unobserved family and community effects on infant mortality in Malawi. Genus LIV(1–2):141–164.Google Scholar
  35. Millard, A. 1994A Causal model of high rates of child mortalitySocial Science and Medecine38253268CrossRefGoogle Scholar
  36. Mosley, W.H., Chen, L.C. 1984Child survival strategies for researchPopulation Development Review102545CrossRefGoogle Scholar
  37. National Statistical Office [Malawi] and ORC Macro. (2001). Malawi Demographic and Health Survey 2000. Zomba, Malawi and Calverton, Maryland, USA: National Statistical Office [Malawi] and ORC Macro.Google Scholar
  38. Rabe-Heskesth, S. & Everitt, B. (2000). A Handbook of Statistical Analysis Using Stata, 2nd ed. Chapman and Hall/CRC.Google Scholar
  39. Sastry, N. 1997Family-level clustering of childhood mortality risk in Northeast BrazilPopulation Studies51245261CrossRefGoogle Scholar
  40. Spiegelhalter D., Best N., Carlin B., & Van der Line A. (2002). Bayesian measures of models complexity and fit. Journal of the Royal Statistical Society Series. B(64): 1–34Google Scholar
  41. Timaeus, I., Harris, K. & Fairbarn, F. (1998). Can use of health care explain sex differentials in child mortality in the developing world? In: United Nations (ed.), Too Young to Die: Genes or Gender? New york: United Nations Secretariat.Google Scholar
  42. UNICEF in Malawi and Government of Malawi (1993). Situation Analysis of Poverty in Malawi. Mantfort press, Limbe.Google Scholar
  43. Whitworth, A., Stephenson, R. 2002Birth spacing, sibling rivalry and child mortality in IndiaSocial Science and Medicine5521072119CrossRefGoogle Scholar
  44. WHO (1998). WHO Global Database on Child Growth and Malnutrition. Geneva: WHO.Google Scholar
  45. Woldemicael, G. (1999), Infant and child mortality in Eritrea: Levels, trends and determinants. Doctoral Dissertation, Demography Unit, Stockholm University.Google Scholar
  46. World Bank (2000). Profile of Poverty in Malawi, 1998. Poverty Analysis of the Malawian Integrated Household Survey, 1997–1998. Washington, DC: The World Bank.Google Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  1. 1.Clinical Sciences Research Institute, CSB, UHCW CampusWarwick Medical SchoolCoventryUK
  2. 2.Department of StatisticsStockholm UniversityStockholmSweden

Personalised recommendations