Skip to main content

Competing risks regression with dependent multiple spells: Monte Carlo evidence and an application to maternity leave


Copulas are a convenient tool for modelling dependencies in competing risks models with multiple spells. This paper introduces several practical extensions to the nested copula model and focuses on the choice of the hazard model and copula. A simulation study looks at the relevance of the assumed parametric or semiparametric model for hazard functions, copula and whether a full or partial maximum likelihood approach is chosen. The results show that the researcher must be careful which hazard is being specified as similar functional form assumptions for the subdistribution and cause-specific hazard will lead to differences in estimated cumulative incidences. Model selection tests for the choice of the hazard model and copula are found to provide some guidance for setting up the model. The nice practical properties and flexibility of the copula model are demonstrated with an application to a large set of maternity leave periods of mothers for up to three maternity leave periods.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4


  • Arntz, M., Dlugosz, S., & Wilke, R. A. (2017). The sorting of female careers after first birth: a competing risks analysis of out of work duration. Oxford Bulletin of Economics and Statistics, 79, 689–716.

    Article  Google Scholar 

  • Bakoyannis, G., & Touloumi, G. (2012). Practical methods for competing risks data: a review. Statistical Methods in Medical Research, 21, 257–272.

    Article  MathSciNet  Google Scholar 

  • Beblo, M., Bender, S., & Wolf, E. (2008). Establishment-level wage effects of entering motherhood. Oxford Economic Papers, 61, 11–34.

    Article  Google Scholar 

  • Beyersmann, J., Latouche, A., Bucholz, A., & Schumacher, M. (2009). Simulating competing risks data in survival analysis. Statistics in Medicine, 28, 956–971.

    Article  MathSciNet  Google Scholar 

  • Bouaziz, O., & Nuel, G. (2016). L0 regularisation for the estimation of piecewise constant hazard rates in survival analysis. arXiv:1609.04595v2

  • Braekers, R., & Veraverbeke, N. (2005). A copula-graphic estimator for the conditional survival function under dependent censoring. Canadian Journal of Statistics, 33, 429–447.

    Article  MathSciNet  Google Scholar 

  • Budig, M. J., & England, P. (2001). The wage penalty for motherhood. American Sociological Review, 66, 204–225.

    Article  Google Scholar 

  • Carrière, J. F. (1994). Dependent decrement theory. Transactions of Society of Actuaries, 46, 45–74.

    Google Scholar 

  • Colvert, R. E., & Boardman, T. J. (1976). Estimation in the piece-wise constant hazard rate model. Communications in Statistics - Theory and Methods, 5, 1013–1029.

    Article  MathSciNet  Google Scholar 

  • Craiu, R. V., & Duchesne, T. (2004). Inference based on the EM algorithm for the competing risks model with masked causes of failure. Biometrika, 91, 543–558.

    Article  MathSciNet  Google Scholar 

  • Craiu, R. V., & Lee, T. C. M. (2005). Model selection for the competing-risks model with and without masking. Technometrics, 47, 457–467.

    Article  MathSciNet  Google Scholar 

  • de Uña-Álvarez, J., & Veraverbeke, N. (2017). Copula-graphic estimation with left-truncated and right-censored data. Statistics, 51, 387–403.

    Article  MathSciNet  Google Scholar 

  • Emura, T., Matsui, S., & Rondeau, V. (2019). Survival Analysis with Correlated Endpoints: Joint Frailty-Copula Models, JSS Research Series in Statistics, Springer.

  • Emura, T., Shih, J. H., Ha, I. D., & Wilke, R. A. (2020). Comparison of the marginal hazard model and the subdistribution hazard model for competing risks under an assumed copula. Statistical Methods in Medical Research, 29, 2307–2327.

    Article  MathSciNet  Google Scholar 

  • Fine, J. P., & Gray, R. J. (1999). A proportional hazard model for the subdistribution of a competing risk. Journal of the American Statistical Association, 94, 496–509.

    Article  MathSciNet  Google Scholar 

  • Fitzenberger, B., Steffes, S., & Strittmatter, A. (2016). Return-to-job during and after parental leave The. International Journal of Human Resource Management, 27(8), 803–831.

    Article  Google Scholar 

  • Gangl, M., & Ziefle, A. (2009). Motherhood, labor force behavior, and women’s careers: An empirical assessment of the wage penalty for motherhood in Britain. Germany, and the United States, Demography, 46(2), 341–369.

    Google Scholar 

  • Ha, I. D., Kim, J. M., & Emura, T. (2019). Profile likelihood approaches for semiparametric copula and frailty models for clustered survival data. Journal of Applied Statistics, 46, 2553–2571.

    Article  MathSciNet  Google Scholar 

  • Hochfellner, D., Müller, D., & Wurdack, A. (2012). Biographical data of social insurance agencies in Germany: Improving the content of administrative data. Journal of Contextual Economics: Schmollers Jahrbuch, 132(3), 443–451.

    Google Scholar 

  • Joe, H. (2005). Asymptotic efficiency of the two-stage estimation method for copula-based models. Journal of Multivariate Analysis, 94, 401–419.

    Article  MathSciNet  Google Scholar 

  • Kyyrä, T. (2009). Marginal effects for competing risks models with piecewise constant hazards. Oxford Bulletin of Economics and Statistics, 71, 539–565.

    Article  Google Scholar 

  • Lancaster, T. (1990). The Econometric Analysis of Transition Data. Econometric Society Monographs. Cambridge: Cambridge University Press.

    Article  MATH  Google Scholar 

  • Lawless, J. F. (2003). Statistical Models and Methods for Lifetime Data (2nd ed.). New York: Wiley.

    MATH  Google Scholar 

  • Lo, S. M. S., & Wilke, R. A. (2010). A copula model for dependent competing risks. Journal of the Royal Statistical Society Series C, 59, 359–376.

    Article  MathSciNet  Google Scholar 

  • Lo, S. M. S., & Wilke, R. A. (2014). A regression model for the Copula–Graphic estimator. Journal of Econometric Methods, 3, 20–41.

    Article  MathSciNet  Google Scholar 

  • Lo, S. M. S., Mammen, E., & Wilke, R. A. (2020). A nested copula duration model for competing risks with multiple spells. Computational Statistics and Data Analysis, 150, 106986, ISSN 0167–9473.

  • Nelsen, R. B. (2006). An Introduction to Copulas (2nd ed.). New York: Springer.

    MATH  Google Scholar 

  • Rivest, L., & Wells, M. T. (2001). A Martingale Approach to the Copula–Graphic estimator for the survival function under dependent censoring. Journal of Multivariate Analysis, 79, 138–155.

    Article  MathSciNet  Google Scholar 

  • Rodrigues, B., & Vergnat, V. (2019). The time and the transitions back to work in France after maternity. Review of Economics of the Household, 17(3), 861–888.

    Article  Google Scholar 

  • Schönberg, U., & Ludsteck, J. (2007). Maternity leave legislation, female labor supply, and the family wage gap. IZA Discussion Paper No. 2699, Institute of Labor Economics (IZA).

  • Sklar, A. (1959). Fonctions de répartition à n dimensions et leurs marges. Publ. Inst. Statist. Univ. Paris, 8, 229–231.

    MathSciNet  MATH  Google Scholar 

  • Trivedi, P. K., & Zimmer, D. M. (2005). Copula Modeling: An Introduction for Practicioners. Foundations and Trends in Econometrics, 1, 1–111.

    Article  Google Scholar 

  • Vuong, Q. (1989). Likelihood ratio tests for model selection and non-nested hypotheses. Econometrica, 57, 307–33.

    Article  MathSciNet  Google Scholar 

  • Waldfogel, J. (1997). The effect of children on women’s wages. American Sociological Review, 62, 209–217.

    Article  Google Scholar 

  • Zheng, M., & Klein, J. P. (1995). Estimates of marginal survival for dependent competing risks based on assumed copula. Biometrika, 82, 127–138.

    Article  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Ralf A. Wilke.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary material 1 (PDF 3619 KB)



1.1 Proof of Proposition 2

To simplify the notation, we omit index k and \({\varvec{\beta }}_k\). For the same reason, we treat all relevant functionals to be sufficiently smooth such that they are differentiable and integrable in t and differentiable in \({\varvec{x}}\). For example the PWCON model has a discontinuous cause-specific hazard in t and would require a combination of summation and integration (see Kyrrä, 2009). Without that this changes the nature of the results. Let

$$\begin{aligned} f_{j}(t;\,{\varvec{x}})= & {} \lambda _{j}(s;\,{\varvec{x}}) S(s;\,{\varvec{x}}) \end{aligned}$$

and therefore \(Q_{j}(t;\,{\varvec{x}}) = \int _0^{t} f_{j}(s;\,{\varvec{x}})\mathrm{d}s\). We assume \(f'_{jl}(t;\,{\varvec{x}})=\partial f_{j}(t;\,{\varvec{x}})/\partial x_l\) is bounded and there exists an interval for t such that \(f'_{jl}(t;\,{\varvec{x}})\) has the same sign for all \(t \in [t_1, t_2)\).

We have

$$\begin{aligned} Q'_{jl}(t_2;\,{\varvec{x}})= & {} \int _0^{t_2}f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s\\= & {} \int _0^{t_1} f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s + \int _{t_1}^{t_2} f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s. \end{aligned}$$

The sign of \(Q'_{jl}(t_1;\,{\varvec{x}})\) is different from \(Q'_{jl}(t_2;\,{\varvec{x}})\) if

$$\begin{aligned} (C1)&\left| \int _0^{t_1} f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s \right| < \left| \int _{t_1}^{t_2}f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s \right| , \text {and} \\ (C2)&{\mathrm{{sign}}}\left( \int _0^{t_1}f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s \right) \ne {\mathrm{{sign}}}\left( \int _{t_1}^{t_2}f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s \right) . \end{aligned}$$

Without loss of generality, we assume that

$$\begin{aligned} \int _0^{t_1}f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s >0 \end{aligned}$$


$$\begin{aligned} \int _{t_1}^{t_2} f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s <0. \end{aligned}$$

The above conditions C1 and C2 can be combined as

$$\begin{aligned} (C3)&\int _0^{t_1} f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s < -\int _{t_1}^{t_2} f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s. \end{aligned}$$

Let \(s_1 = \arg \sup _{t\in [0,t_1)} f'_{jl}(s;\,{\varvec{x}})\) and \(s_2 = \arg \sup _{t\in [t_1,t_2)} f'_{jl}(s;\,{\varvec{x}})\). Then, \(f'_{jl}(s_2;\,{\varvec{x}})<0\) and takes the least negative value of \(f'_{jl}(t;\,{\varvec{x}})\) for \(t\in [t_1,t_2)\). We therefore have

$$\begin{aligned} 0<\int _0^{t_1} f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s\le & {} \int _0^{t_1} f'_{jl}(s_1;\,{\varvec{x}}) \ \mathrm{d}s \equiv t_1 f'_{jl}(s_1;\,{\varvec{x}}) \text {, and}\\ 0<-(t_2-t_1) f'_{jl}(s_2;\,{\varvec{x}})\equiv & {} -\int _{t_1}^{t_2} f'_{jl}(s_2;\,{\varvec{x}}) \ \mathrm{d}s \le -\int _{t_1}^{t_2} f'_{jl}(s;\,{\varvec{x}}) \ \mathrm{d}s. \end{aligned}$$

Hence, C3 holds if there existed \(t_1\) and \(\epsilon = t_2 - t_1 >0\) such that :

$$\begin{aligned} 0< & {} t_1 f'_{jl}(s_1;\,{\varvec{x}})< - \epsilon f'_{jl}(s_2;\,{\varvec{x}}),\nonumber \\ 0< & {} \frac{t_1}{\epsilon } f'_{jl}(s_1;\,{\varvec{x}}) < -f'_{jl}(s_2;\,{\varvec{x}}). \end{aligned}$$

Equation (21) holds if (i) \(f'_{jl}(s_2;\,{\varvec{x}}) <0\) and (ii) \(|f'_{jl}(s_2;\,{\varvec{x}})|>c f'_{jl}(s_1;\,{\varvec{x}}) >0\) for some \(c>0\). c is small if \(t_1\) is small or \(t_2-t_1\) is large. It depends on the model and covariate \(x_l\), whether these conditions are satisfied or not. This is illustrated and discussed in more detail in what follows.

Note that

$$\begin{aligned} f'_{jl}(s;\,{\varvec{x}})= & {} \lambda _j(s;\,{\varvec{x}})S'(s;\,{\varvec{x}}) + \lambda '_{jl}(s;\,{\varvec{x}})S(s;\,{\varvec{x}})\\= & {} -f_{j}(s;\,{\varvec{x}})(\Lambda '_{1l}(s;\,{\varvec{x}}) +\Lambda '_{2l}(s;\,{\varvec{x}})) +\lambda '_{jl}(s;\,{\varvec{x}}) f_j(s;\,{\varvec{x}})/\lambda _j(s;\,{\varvec{x}})\\= & {} -f_j(s;\,{\varvec{x}})[\Lambda '_{1l}(s;\,{\varvec{x}}) +\Lambda '_{2l}(s;\,{\varvec{x}}) - \lambda '_{jl}(s;\,{\varvec{x}}) /\lambda _j(s;\,{\varvec{x}})]. \end{aligned}$$

Condition (i) \(f'_{jl}(s_2;\,{\varvec{x}}) <0\) requires

$$\begin{aligned} \Lambda '_{1l}(s_2;\,{\varvec{x}}) +\Lambda '_{2l}(s_2;\,{\varvec{x}}) > \Lambda '_{jl}(s_2;\,{\varvec{x}}) /\lambda _j(s_2;\,{\varvec{x}}), \end{aligned}$$

which may be the case or not. Take as an example a proportional hazard model \(\Lambda _j(t;\,{\varvec{x}})=\Lambda _{j0}(t)\phi _j({\varvec{x}})\), \(\lambda _j(t;\,{\varvec{x}})=\lambda _{j0}(t)\phi _j({\varvec{x}})\) and \(\phi _j({\varvec{x}})>0\). In this case (22) becomes

$$\begin{aligned} \Lambda _{10}(s_2)\phi '_{1l}({\varvec{x}}) + \Lambda _{20}(s_2)\phi '_{2l}({\varvec{x}})> & {} \phi '_{jl}({\varvec{x}})/\phi _{j}({\varvec{x}}). \end{aligned}$$

This likely holds for \(s_2\) large as \(\Lambda _{j0}(s)\) grows to \(\infty\) as t increases, whenever \(\phi '_{jl}({\varvec{x}})>0\) for \(j=1,2\). (i) therefore cannot be ruled out even under strong restrictions on the role of the covariates. For condition (ii) to hold, we need for some \(c>0\)

$$\begin{aligned}&|f_j(s_2;\,{\varvec{x}})[\Lambda '_{1l}(s_2;\,{\varvec{x}}) +\Lambda '_{2l}(s_2;\,{\varvec{x}}) - \Lambda '_{jl}(s_2;\,{\varvec{x}}) /\lambda _j(s_2;\,{\varvec{x}})]|\nonumber \\&\quad > c|f_j(s_1;\,{\varvec{x}})[\Lambda '_{1l}(s_1;\,{\varvec{x}}) +\Lambda '_{2l}(s_1;\,{\varvec{x}}) - \lambda '_{jl}(s_1;\,{\varvec{x}}) /\lambda _j(s_1;\,{\varvec{x}})]|. \end{aligned}$$

Again, this may be true or not. Take again as an example \(\Lambda _j(t;\,{\varvec{x}})=\Lambda _{j0}(t)\phi _j({\varvec{x}})\), the above condition becomes

$$\begin{aligned}&|f_j(s_2;\,{\varvec{x}})[\Lambda _{10}(s_2)\phi '_{1l}({\varvec{x}}) +\Lambda _{20}(s_2)\phi '_{2l}({\varvec{x}}) - \phi '_{jl}({\varvec{x}})/\phi _j({\varvec{x}})]|\nonumber \\&\quad > c|f_j(s_1;\,{\varvec{x}})[\Lambda _{10}(s_1)\phi '_{1l}({\varvec{x}}) +\Lambda _{20}(s_1)\phi '_{2l}({\varvec{x}}) - \phi '_{jl}({\varvec{x}})/\phi _j({\varvec{x}})]|. \end{aligned}$$

This generally holds if \(f_j(s_2;\,{\varvec{x}})>cf_j(s_1;\,{\varvec{x}})\) since by definition \(\Lambda _{j0}(s_2) >\Lambda _{j0}(s_1)\) for all \(s_2>s_1\). Condition (ii) therefore holds for c small enough. We have therefore illustrated that even for the proportional hazards model, where the direction of the partial effect on the hazard is unique for all t, there is no analogous result for \(Q'_{jl}(t;\,{\varvec{x}})\) as the direction of partial covariate effect is not restricted.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lipowski, C., Lo, S.M.S., Shi, S. et al. Competing risks regression with dependent multiple spells: Monte Carlo evidence and an application to maternity leave. Jpn J Stat Data Sci 4, 953–981 (2021).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Copula
  • Competing risks
  • Repeated occurrences
  • Maternity leave