# The Frailty Concept

## Abstract

An individual said to be frail if he or she is much more susceptible (exposed or infected) to adverse events than others. Clayton (1978) introduced the term frailty to indicate that different individuals are at risk even though on the surface they may appear to be quite similar with respect to measurable attributes such as age, gender, weight, etc. He used the term frailty to represent an unobservable random effect shared by subjects with similar (unmeasured) risks in the analysis of mortality rates. A random effect describes excess risk or frailty for distinct categories, such as individuals or families, over and above any measured covariates. Thus, random effect or frailty models have been introduced into the statistical literature in an attempt to account for the existence of unmeasured attributes such as genotype that do introduce heterogeneity into a study population. It is recognized that individuals in the same family are more similar than the individuals in different families because they share similar genes and similar environment. Thus, frailty or random effect models try to account for correlations within groups. Such groups arise naturally in those studies involving two or more failure times on the same individual subject. These failure times may be times to the recurrence of the same event or times to the occurrence of different types of events. Examples include the time sequences of asthmatic attacks, infection episodes, tumor diagnosis, tumor recurrences or bleeding incidents in individual subjects (Prentice et al. 1981).

## References

- Aalen, O.O.: Two examples of modelling heterogeneity in survival analysis. Scand. J. Stat.
**14**, 19–25 (1987)Google Scholar - Aalen, O.O.: Heterogeneity in survival analysis. Stat. Med.
**7**, 1121–1137 (1988)CrossRefGoogle Scholar - Babikar, A., Cuzick, J.: A simple frailty model for family studies with covariates. Stat. Med.
**13**, 1679–1692 (1994)CrossRefGoogle Scholar - Clayton, D.G.: A model for association in bivariate life tables and its application in epidemiological studies of familial tendency in chronic disease incidence. Biometrika
**65**, 141–151 (1978)MathSciNetCrossRefGoogle Scholar - Cox, D.R.: Regression models and life tables (with discussions). J. R. Stat. Soc., B
**34**, 187–220 (1972)Google Scholar - Elbers, C., Rider, G.: True and spurious duration dependence: the identifibility of the proportional hazard model. Rev. Econ. Stud.
**49**, 403–409 (1982)CrossRefGoogle Scholar - Flinn, C.J., Heckman, J.J.: New methods for analyzing individual event histories. Social. Methodol. pp. 99–140 (1982)CrossRefGoogle Scholar
- Heckman, J., Singer, B.: The identifiability of the proportional hazard model. Rev. Econ. Stud.
**51**(2), 231–241 (1984)CrossRefGoogle Scholar - Hedeker, D., Siddiqui, O., Hu, F.B.: Random effects regression analysis of correlated group time survival data. School of Public Health and Prevention Research Cancer. University of Illinois, Chicago (1996)Google Scholar
- Holt, J.D., Prentice, R.L.: Survival analysis in twin studies and matched pair experiments. Biometrika
**61**(1), 17–30 (1974)MathSciNetCrossRefGoogle Scholar - Honore, B.E.: Identification results for duration models with multiple spells. Rev. Econ. Stud.
**60**, 241–246 (1993)CrossRefGoogle Scholar - Hougaard, P., Muglogaard., Borch-Johnsen, K.: Heterogeneity models of disease susceptibility with application to diabetic nephropathy. Biometrics
**50**(4), 1178–1188 (1994)CrossRefGoogle Scholar - Hougaard, P.: Frailty models for survival data. Lifetime Data Analysis,
**1**, 255–274 (1995)MathSciNetCrossRefGoogle Scholar - Hougaard, P.: A class of multivariate failure time distributions. Biometrika
**73**, 671–678 (1986a)MathSciNetzbMATHGoogle Scholar - Hougaard, P.: Survival models for hetrogeneous populations derived from stable distributions. Biometrika
**73**, 387–396 (1986b)MathSciNetCrossRefGoogle Scholar - Iachine, I.A., Yashin, A.I.: Identifiability of bivariate frailty models based on additive independent components. Research Report 8, Department of Statistics and Demography, Odense University, Denmark (1998)Google Scholar
- Iachine, I.A.: . Identifiability of bivariate frailty models. Working Paper, Department of Statistics and Demography, University of Southern Denmark, Denmark (2006)Google Scholar
- Keiding, N., Andersen, P.K., Klein, J.P.: The role of frailty models and accelerated failure time models in describing heterogeneity due to omitted covariates. Stat. Med.
**16**(1–3), 215–224 (1997)CrossRefGoogle Scholar - Keyfitz, N., Littman, G.: Mortality in a heterogeneous population. Popul. Stud.
**33**, 333–342 (1979)CrossRefGoogle Scholar - Lancaster, T.: The Economic Analysis of Transition Data. University Press Cambridge, London (1990)zbMATHGoogle Scholar
- Lindstorm, D.P.: Economic opportunities in Mexico and return to the United States. Demography
**33**, 357–374 (1996)CrossRefGoogle Scholar - MacLachlan, G.J., Basford, K.E.: Mixture models: Inference and applications to clustering. Statistics:Textbooks and monographs, Vol. 84. Marcel Dekker, New York (1998)Google Scholar
- McCall, B.P.: Testing the proportional hazard assumptions in the presence of unmeasured heterogeneity: an application to the unemployment durations of displaced workers. J. Appl. Econ., B
**44**, 226–233 (1994)Google Scholar - Melino, A., Sueyoshi, G.T.: A simple approach to the identifiability of the proportional hazard model. Econ. Lett.
**33**, 63–68 (1990)CrossRefGoogle Scholar - Oakes, D.: Bivariate survival models induced by frailties. J. Am. Stat. Assoc.
**84**, 487–493 (1989)MathSciNetCrossRefGoogle Scholar - Oakes, D.: A model for association in bivariate survival data. J. R. Stat. Soc., B
**44**, 414–493 (1982)MathSciNetzbMATHGoogle Scholar - Oakes, D.: Semiparametric inference in bivariate survival data. Biometrika
**73**, 353–361 (1986)MathSciNetzbMATHGoogle Scholar - Parner, E.: Asymptotic theory for the correlated gamma-frailty model. Ann. Stat.
**26**(1), 183–214 (1998)MathSciNetCrossRefGoogle Scholar - Pickles, A., Crouchley, R.: A comparison of frailty models for multivariate survival data. Stat. Med.
**14**, 1447–1461 (1995)CrossRefGoogle Scholar - Prentice, R.L., Williams, B.J., Peterson, A.V.: On the regression analysis of multivariate failure time data. Biometrika
**68**, 373–379 (1981)MathSciNetCrossRefGoogle Scholar - Ridder, G.: The non-parametric identification of generalized accelerated failure time models. Rev. Econ. Stud.
**57**(2), 167–181 (1990)MathSciNetCrossRefGoogle Scholar - Shih, J.H., Louis, T.A.: Inferences on the association parameter in copula models for bivariate data. Biometrics
**51**(4), 1384–1399 (1995)MathSciNetCrossRefGoogle Scholar - Trussel, J., Richards, T.: Correcting for unobserved heterogeneity in hazard models using Heckman-Singer procedure. Social. Methodol. pp. 242–276 (1985)Google Scholar
- Vaupel, J.W.: Inherited frailty and longevity. Demography
**25**(2), 139–149 (1988)CrossRefGoogle Scholar - Vaupel, J.W., Manton, K.G., Stallard, E.: The impact of heterogeneity on individual frailty on the dynamic of mortality. Demography
**16**(3), 439–454 (1979)CrossRefGoogle Scholar - Yashin, A.I., Iachine, I.A., Begun, A.S.: Mortality modeling: a review. Math. Popul. Stud.
**8**(4), 305–332 (2000)MathSciNetCrossRefGoogle Scholar - Zelterman, D.: A statistical distribution with an unbounded hazard function and its application to a theory from demography. Biometrics
**48**, 807–818 (1992)CrossRefGoogle Scholar