• No results found

Modelling long term survival with non-proportional hazards Perperoglou, A.

N/A
N/A
Protected

Academic year: 2021

Share "Modelling long term survival with non-proportional hazards Perperoglou, A."

Copied!
2
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

Modelling long term survival with non-proportional hazards

Perperoglou, A.

Citation

Perperoglou, A. (2006, October 18). Modelling long term survival with non-proportional hazards. Retrieved from

https://hdl.handle.net/1887/4918

Version:

Corrected Publisher’s Version

License:

Licence agreement concerning inclusion of doctoral thesis in the Institutional Repository of the University of

Leiden

Downloaded from:

https://hdl.handle.net/1887/4918

(2)

Curriculum Vitae

Aris Perperoglou was born in Chios, Greece in 1976. He obtained his high school (lyceum∗) diploma in 1994 and was accepted to study Statistics at the Athens University of Business and Economics. During his studies the author worked as a guest researcher in the National Centre for Social Research (1997) doing statistical analysis on demographic data from the Balkan countries. For a short period (1998-1999) the author was absorbed into economics and worked in Select Investments S.A. performing technical analysis of the Athens Stock Exchange. In 2000 he finally graduated from university and started a Masters degree in Biostatistics at the Department of Mathematics of the University of Athens. At the same time he was working as a researcher at the department of Breast Oncology in IASO hospital (Athens), under the supervision of Dr. An-tonis Keramopoullos. Together they organized a department of Research and Statistics in which the author is still involved up to date, providing statistical advice. In June 29nd, 2002 the author defended his Masters dissertation on the survival analysis of breast cancer patients and in July 1st he moved in Leiden to start his Ph.D. research, funded by the ZonMW project (ZON 912.02.015). During his stay in Leiden he quit smoking twice.

Latin Lyceum, from Greekλ ´υκιoν the school outside Athens where Aristotle taught

(335-323 B.C.)

Referenties

GERELATEERDE DOCUMENTEN

Starting point is a Cox model with p covariates and time varying effects modeled by q time functions (constant included), leading to a p × q structure matrix that contains

In order to fit a model with time varying effects of the covariates we first had to expand the data to create the different risk sets using the function expand.breakpoints created

Table 4.1: Average coefficient estimates and standard errors in brackets, under the three different models, proportional hazards (PH), Burr (B) and relaxed Burr (RB), for

Although the results from a Burr model and a reduced rank model might be very close, especially in terms of survival functions, a Burr model cannot reveal anything about the nature of

der the assumed model. Another way is to assume a parametric form for φ which will lead to a mixing distribution. In such a case, the mean could follow a gamma distribution with mean

At the same time, by using flexible time functions and letting the rank of the model decide on the pattern of the covariate effects the problem of choosing the time functions can

When expanding the baseline hazard, the function assigns a zero value in the time points of censoring, while when expanding a cumulative baseline hazard, the function assigns the

Zhang, Inference in generalized additive mixed models by using smoothing splines, Journal of the Royal Statistical Society B, 61 (1999), pp... Lumley, Survival: survival