Methods

In this section, we outline the statistical background for the tools incorporated in PyDTS. We commence with some definitions, present the collapsed log-likelihood approach and the estimation procedure of Lee et al. (2018) [4], introduce our estimation method [1]-[2], and conclude with evaluation metrics. For additional details, check out the references.

References

[1] Meir, Tomer*, Gutman, Rom*, and Gorfine, Malka, "PyDTS: A Python Package for Discrete-Time Survival Analysis with Competing Risks" (2022)

[2] Meir, Tomer and Gorfine, Malka, "Discrete-time Competing-Risks Regression with or without Penalization" (2023)

[3] Allison, Paul D. "Discrete-Time Methods for the Analysis of Event Histories" Sociological Methodology (1982), doi: 10.2307/270718

[4] Lee, Minjung and Feuer, Eric J. and Fine, Jason P. "On the analysis of discrete time competing risks data" Biometrics (2018) doi: 10.1111/biom.12881

[5] Kalbfleisch, John D. and Prentice, Ross L. "The Statistical Analysis of Failure Time Data" 2nd Ed., Wiley (2011) ISBN: 978-1-118-03123-0

[6] Klein, John P. and Moeschberger, Melvin L. "Survival Analysis", Springer (2003) ISBN: 978-0-387-95399-1