Page 153 - Special Topic Session (STS) - Volume 3

STS535 Edsel A. P. et al.
within each sub-model could then be performed separately, but note that
these sub-model likelihood functions depend on data from the other
components. Also, because the nonparametric baseline hazard rate functions
are being evaluated at the effective age functions, to obtain the estimates of
their associated cumulative hazard functions, a time-change approach
implemented in [4] is required. Other inferential aspects will be discussed at
the WSC talk by the first author.

References
1. P. Andersen, O. Borgan, R. Gill, and N. Keiding. Statistical Models Based
on Counting Processes. Springer-Verlag, New York, 1993.
2. J. Jacod. Multivariate point processes: predictable projection, radon-
nikodym derivatives, representation of martingales. Z. Wahrsch. verw.
Geb., 34:225–244, 1975.
3. E. Pen˜a and M. Hollander. Mathematical Reliability: An Expository
Perspective (eds., R. Soyer, T. Mazzuchi and N. Singpurwalla), chapter 6.
Models for Recurrent Events in Reliability and Survival Analysis, pages
105–123. Kluwer Academic Publishers, 2004.
4. Edsel Pen˜a, Elizabeth Slate, and Juan Ramon Gonzalez. Semiparametric
inference for a general class of models for recurrent events. Journal of
Statistical Planning and Inference, 137:1727–1747, 2007.

142 | I S I W S C 2 0 1 9