Statistical Science

Verbal Autopsy Methods with Multiple Causes of Death

Gary King and Ying Lu

Full-text: Open access


Verbal autopsy procedures are widely used for estimating cause-specific mortality in areas without medical death certification. Data on symptoms reported by caregivers along with the cause of death are collected from a medical facility, and the cause-of-death distribution is estimated in the population where only symptom data are available. Current approaches analyze only one cause at a time, involve assumptions judged difficult or impossible to satisfy, and require expensive, time-consuming, or unreliable physician reviews, expert algorithms, or parametric statistical models. By generalizing current approaches to analyze multiple causes, we show how most of the difficult assumptions underlying existing methods can be dropped. These generalizations also make physician review, expert algorithms and parametric statistical assumptions unnecessary. With theoretical results, and empirical analyses in data from China and Tanzania, we illustrate the accuracy of this approach. While no method of analyzing verbal autopsy data, including the more computationally intensive approach offered here, can give accurate estimates in all circumstances, the procedure offered is conceptually simpler, less expensive, more general, as or more replicable, and easier to use in practice than existing approaches. We also show how our focus on estimating aggregate proportions, which are the quantities of primary interest in verbal autopsy studies, may also greatly reduce the assumptions necessary for, and thus improve the performance of, many individual classifiers in this and other areas. As a companion to this paper, we also offer easy-to-use software that implements the methods discussed herein.

Article information

Statist. Sci., Volume 23, Number 1 (2008), 78-91.

First available in Project Euclid: 7 July 2008

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Verbal autopsy cause-specific mortality cause of death survey research classification sensitivity specificity


King, Gary; Lu, Ying. Verbal Autopsy Methods with Multiple Causes of Death. Statist. Sci. 23 (2008), no. 1, 78--91. doi:10.1214/07-STS247.

Export citation


  • Anker, M. (2003). Investigating Cause of Death During an Outbreak of Ebola Virus Haemorrhagic Fever: Draft Verbal Autopsy Instrument. World Health Organization, Geneva.
  • Boulle, A., Chandramohan, D. and Weller, P. (2001). A case study of using artificial neural networks for classifying cause of death from verbal autopsy. Internat. J. Epidemiology 30 515–520.
  • Chandramohan, D., Maude, G. H., Rodrigues, L. C. and Hayes, R. J. (1994). Verbal autopsies for adult deaths: Issues in their development and validation. Internat. J. Epidemiology 23 213–222.
  • Chandramohan, D., Setel, P. and Quigley, M. (2001). Effect of misclassification of causes of death in verbal autopsy: Can it be adjusted. Internat. J. Epidemiology 30 509–514.
  • Chang, C.-C. and Lin, C.-J. (2001). LIBSVM: A library for support vector machines. Available at
  • Dawes, R. M., Faust, D. and Meehl, P. E. (1989). Clinical versus actuarial judgement. Science 243 1668–1674.
  • Franklin, C. H. (1989). Estimation across data sets: Two-stage auxiliary instrumental variables estimation. Political Analysis 1 1–23.
  • Gajalakshmi, V. and Peto, R. (2004). Verbal autopsy of 80,000 adult deaths in Tamilnadu, South India. BMC Public Health 4.
  • Gelman, A., King, G. and Liu, C. (1999). Not asked and not answered: Multiple imputation for multiple surveys. J. Amer. Statist. Assoc. 93 846–857.
  • Hand, D. J. (2006). Classifier technology and the illusion of progress. Statist. Sci. 21 1–14.
  • Hopkins, D. and King, G. (2007). Extracting systematic social science meaning from text. Available at
  • Hoppa, R. D. and Vaupel, J. W., eds. (2002). Paleodemography. Cambridge Univ. Press.
  • Kalter, H. (1992). The validation of interviews for estimating morbidity. Health Policy and Planning 7 30–39.
  • Levy, P. S. and Kass, E. H. (1970). A three population model for sequential screening for Bacteriuria. Amer. J. Epidemiology 91 148–154.
  • Lopez, A., Ahmed, O., Guillot, M., Ferguson, B. D., Salomon, J. A., Murray, C. J. L. and Hill, K. H. (2000). World Mortality in 2000: Life Tables for 191 Countries. World Health Organization, Geneva.
  • Mathers, C. D., Ma Fat, D., Inoue, M., Rao, C. and Lopez, A. (2005). Counting the dead and what they died from: An assessment of the global status of cause of death data. Bulletin of the World Health Organization 83 171–177c.
  • Maude, G. H. and Ross, D. A. (1997). The effect of different sensitivity, specificity and cause-specific mortality fractions on the estimation of differences in cause-specific mortality rates in children from studies using verbal autopsies. Internat. J. Epidemiology 26 1097–1106.
  • Morris, S. S., Black, R. E. and Tomaskovic, L. (2003). Predicting the distribution of under-five deaths by cause in countries without adequate vital registration systems. Internat. J. Epidemiology 32 1041–1051.
  • Pacque-Margolis, S., Pacque, M., Dukuly, Z., Boateng, J. and Taylor, H. R. (1990). Application of the verbal autopsy during a clinical trial. Social Science Medicine 31 585–591.
  • Quigley, M. A., Chandramohan, D., Setel, P., Binka, F. and Rodrigues, L. C. (2000). Validity of data-derived algorithms for ascertaining causes of adult death in two African sites using verbal autopsy. Tropical Medicine and International Health 5 33–39.
  • Setel, P. W., Whiting, D. R., Hemed, Y., Chandramohan, D., Wolfson, L. J., Alberti, K. G. M. M. and Lopez, A. (2006). Validity of verbal autopsy procedures for determining causes of death in Tanzania. Tropical Medicine and International Health 11 681–696.
  • Setel, P. W., Sankoh, O., Velkoff, V. A., Mathers, C., Gonghuan, Y. et al. (2005). Sample registration of vital events with verbal autopsy: A renewed commitment to measuring and monitoring vital statistics. Bulletin of the World Health Organization 83 611–617.
  • Sibai, A. M., Fletcher, A., Hills, M. and Campbell, O. (2001). Non-communicable disease mortality rates using the verbal autopsy in a cohort of middle aged and older populations in Beirut during wartime, 1983–93. J. Epidemiology and Community Health 55 271–276.
  • Soleman, N., Chandramohan, D. and Shibuya, K. (2005). WHO Technical Consultation on Verbal Autopsy Tools. Geneva. Available at
  • Soleman, N., Chandramohan, D. and Shibuya, K. (2006). Verbal autopsy: Current practices and challenges. Bulletin of the World Health Organization 84 239–245.
  • Thisted, R. A. (1988). Elements of Statistical Computing: Numerical Computation. Chapman and Hall, New York.
  • Yang, G., Rao, C., Ma, J., Wang, L., Wan, X., Dubrovsy, G. and Lopez, A. D. (2005). Validation of verbal autopsy procedures for adult deaths in China. Internat. J. Epidemiology 35 741–748.