Statistical Analysis of Complex Event History Data
Statistical Analysis of Complex Event History Data
Principal investigators
Abstract
The aim of the project "Statistical Analysis of Complex Event History Data" has been to make substantial contributions to the methodology for analysing complex event histories, as indicated by the above mentioned problems, as well as for related ones. Event history data are rarely fully observed, usually events for a subject are only registered if they fall within an observation window, and events outside the window are unknown to the researcher. This is a main reason why special statistical methods are needed to analyse event history data. Modern event history analysis has been developed over the last 30-40 years, motivated mainly by medical research, but also by problems in econometrics and technical reliability, and event history analysis is today an area of statistical science with its own concepts, models, and methods.
Although great advances have been made in event history analysis over the last decades, the field still remains dominated by the classical methods for single event times (Kaplan-Meier estimator, logrank test, Cox regression), and existing methodologies are not always easily adapted to the more ambitious research questions and richer data structures of contemporary research:
Fellows
Vernon Todd Farewell
Bo Henry Lindqvist
Torben Martinussen
