Abstract
For diseases with some level of associated mortality, the case fatality ratio measures the proportion of diseased individuals who die from the disease. In principle, it is straightforward to estimate this quantity from individual follow‐up data that provides times from onset to death or recovery. In particular, in a competing risks context, the case fatality ratio is defined by the limiting value of the sub‐distribution function, F 1(t) = Pr(T ⩽t and J = 1), associated with death, as t → ∞, where T denotes the time from onset to death (J = 1) or recovery (J = 2). When censoring is present, however, estimation of F 1(∞) is complicated by the possibility of little information regarding the right tail of F 1, requiring use of estimators of F 1(t*) or F 1(t *)/(F 1(t *)+F 2(t *)) where t * is large, with F 2(t) = Pr(T ⩽t and J = 2) being the analogous sub‐distribution function associated with recovery. With right censored data, the variability of such estimators increases as t * increases, suggesting the possibility of using estimators at lower values of t * where bias may be increased but overall mean squared error be smaller. These issues are investigated here for non‐parametric estimators of F 1 and F 2. The ideas are illustrated on case fatality data for individuals infected with Severe Acute Respiratory Syndrome (SARS) in Hong Kong in 2003. Copyright © 2006 John Wiley & Sons, Ltd.
Keywords: case fatality ratio, competing risks, inverse probability weighting, non‐parametric maximum likelihood estimation
Contributor Information
Nicholas P. Jewell, Email: jewell@stat.berkeley.edu.
Xiudong Lei, Email: xiudonglei@hotmail.com.
Azra C. Ghani, Email: azra.ghani@lshtm.ac.uk
Christl A. Donnelly, Email: c.donnelly@imperial.ac.uk
Gabriel M. Leung, Email: gmleung@hku.hk
Lai‐Ming Ho, Email: lmho@hkucc.hku.hk.
Benjamin J. Cowling, Email: bcowling@hkucc.hku.hk
Anthony J. Hedley, Email: hrmrajh@hkucc.hku.hk
REFERENCES
- 1. Gaynor JJ, Feuer EJ, Tan CC, Wu DH, Little CR, Straus DJ, Clarkson BD, Brennan MF. On the use of cause‐specific failure and conditional failure probabilities: examples from clinical oncology data. Journal of the American Statistical Association 1993; 88:400–409. [Google Scholar]
- 2. Donnelly CA, Ghani AC, Leung GM, Hedley AJ, Fraser C, Riley S, Abu‐Raddad LJ, Ho L‐M, Thach T‐Q, Chau P, Chan K‐P, Lam T‐H, Tse L‐Y, Tsang T, Liu S‐H, Kong JHB, Lau EMC, Ferguson NM, Anderson RM. Epidemiological determinants of spread of causal agent of severe acute respiratory syndrome in Hong Kong. The Lancet 2003; 361:1761–1766. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 3. Galvani AP, Lei X, Jewell NP. Severe Acute Respiratory Syndrome: temporal stability and geographic variation in cumulative case fatality rates and average doubling times. Emerging Infectious Diseases 2003; 9:991–994. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 4. Ghani AC, Donnelly CA, Cox DR, Griffin JT, Fraser C, Lam TH, Ho LM, Chan WS, Anderson RM, Hedley AJ, Leung GM. Methods for estimating the case fatality rate for a novel, emerging infectious disease. American Journal of Epidemiology 2005; 162:479–486. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 5. Kalbfleisch JD, Prentice RL. The Statistical Analysis of Failure Time Data (2nd edn). Wiley: New York, 2002. [Google Scholar]
- 6. Koul H, Susarla V, Van Ryzin J. Regression analysis with randomly right censored data. Annals of Statistics 1981; 9:1276–1288. [Google Scholar]
- 7. Robins JM, Rotnitzky A. Recovery of information and adjustment for dependent censoring using surrogate markers In AIDS Epidemiology: Methodological Issues, Jewell NP, Dietz K, Farewell V. (eds). Birkhauser: Boston, 1992; 297–331. [Google Scholar]
- 8. Aalen OO, Johansen S. An empirical transition matrix for nonhomogeneous Markov chains based on censored observations. Scandinavian Journal of Statistics 1978; 5:141–150. [Google Scholar]
- 9. Aalen OO. Nonparametric estimation of partial transition probabilities in multiple decrement models. Annals of Statistics 1978; 6:534–545. [Google Scholar]
- 10. Gooley TA, Leisenring W, Crowley J, Storer BE. Estimation of failure probabilities in the presence of competing risks: new representations of old estimators. Statistics in Medicine 1999; 18:695–706. [DOI] [PubMed] [Google Scholar]
- 11. Reid N. Influence functions In Encyclopedia of Statistical Sciences, vol. 4, Kotz S, Johnson NL. (eds). Wiley: New York, 1983; 117–120. [Google Scholar]
- 12. Andersen PK, Borgan O, Gill RD, Keiding N. Statistical Models Based on Counting Processes. Springer: New York, 1993. [Google Scholar]
- 13. Dinse GE, Larson MG. A note on semi‐Markov models for partially censored data. Biometrika 1986; 73:379–386. [Google Scholar]
- 14. Pepe MS. Inference for events with dependent risks in multiple endpoint studies. Journal of the American Statistical Association 1991; 86:770–778. [Google Scholar]
- 15. Lin DY. Non‐parametric inference for cumulative incidence functions in competing risks studies. Statistics in Medicine 1997; 16:901–910. [DOI] [PubMed] [Google Scholar]
- 16. Choudhury JB. Non‐parametric confidence interval estimation for competing risks analysis: application to contraceptive data. Statistics in Medicine 2002; 21:1129–1144. [DOI] [PubMed] [Google Scholar]
- 17. Shao J, Tu D. The Jackknife and Bootstrap. Springer: New York, 1995. [Google Scholar]
- 18. Leung GM, Hedley AJ, Ho L‐M, Chau P, Wong IOL, Thach TQ, Ghani AC, Donnelly CA, Fraser C, Riley S, Ferguson NM, Anderson RM, Tsang T, Leung P‐Y, Wong V, Chann JCK, Tsui E, Lo S‐V, Lam T‐H. The epidemiology of severe acute respiratory syndrome in the 2003 Hong Kong epidemic: an analysis of all 1755 patients. Annals of Internal Medicine 2004; 141:662–673. [DOI] [PubMed] [Google Scholar]
- 19. van der Laan MJ, Robins JM. Unified Methods for Censored Longitudinal Data and Causality. Springer: New York, 2003. [Google Scholar]
- 20. Gill RD, van der Laan MJ, Robins JM. Coarsening at random: characterizations, conjectures, counter‐examples In Proceedings of First Seattle Conference in Biostatistics, Lin D‐Y. (ed.). Springer: Berlin, 1997; 255–294. [Google Scholar]