The Annals of Applied Statistics

Age- and time-varying proportional hazards models for employment discrimination

George Woodworth and Joseph Kadane

Full-text: Open access


We use a discrete-time proportional hazards model of time to involuntary employment termination. This model enables us to examine both the continuous effect of the age of an employee and whether that effect has varied over time, generalizing earlier work [Kadane and Woodworth J. Bus. Econom. Statist. 22 (2004) 182–193]. We model the log hazard surface (over age and time) as a thin-plate spline, a Bayesian smoothness-prior implementation of penalized likelihood methods of surface-fitting [Wahba (1990) Spline Models for Observational Data. SIAM]. The nonlinear component of the surface has only two parameters, smoothness and anisotropy. The first, a scale parameter, governs the overall smoothness of the surface, and the second, anisotropy, controls the relative smoothness over time and over age. For any fixed value of the anisotropy parameter, the prior is equivalent to a Gaussian process with linear drift over the time–age plane with easily computed eigenvectors and eigenvalues that depend only on the configuration of data in the time–age plane and the anisotropy parameter. This model has application to legal cases in which a company is charged with disproportionately disadvantaging older workers when deciding whom to terminate. We illustrate the application of the modeling approach using data from an actual discrimination case.

Article information

Ann. Appl. Stat., Volume 4, Number 3 (2010), 1139-1157.

First available in Project Euclid: 18 October 2010

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Age discrimination thin plate spline smoothness prior discrete proportional hazards semiparametric Bayesian logistic regression


Woodworth, George; Kadane, Joseph. Age- and time-varying proportional hazards models for employment discrimination. Ann. Appl. Stat. 4 (2010), no. 3, 1139--1157. doi:10.1214/10-AOAS330.

Export citation


  • Cox, D. R. (1972). Regression models and life tables. J. Roy. Statist. Soc. Ser. B 34 187–220.
  • Finkelstein, M. O. and Levin, B. (1994). Proportional hazards models for age discrimination cases. Jurimetrics Journal 34 153–171.
  • Gamerman, D. (1997). Sampling from the posterior distribution in generalized linear mixed models. Statistics and Computing 7 57–68.
  • Gastwirth, J. (1992). Employment discrimination: A statistician’s look at analysis of disparate impact claims. Law and Inequality: A Journal of Theory and Practice XI Number 1.
  • Gersch, W. (1982). Smoothness priors. In Encyclopedia of Statistical Sciences (S. Kotz, N. L. Johnson and C. B. Read, eds.) 8 518–526. Wiley, New York.
  • Green, P. J. (1995). Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82 711–732.
  • Kadane, J. B. (1990a). A statistical analysis of adverse impact of employer decisions. J. Amer. Statist. Assoc. 85 925–933.
  • Kadane, J. B. (1990b). Comment: Codifying chance. Statist. Sci. 5 18–20.
  • Kadane, J. B. and Woodworth, G. G. (2004). Hierarchical models for employment decisions. J. Bus. Econom. Statist. 22 182–193.
  • Mosteller, F. and Youtz, C. (1990). Quantifying probabilistic expressions. Statist. Sci. 5 2–12.
  • Wahba, G. (1990). Spline Models for Observational Data. SIAM, Philadelphia.

Supplemental materials