Event History 1: Introduction and Models for Discrete Survival Times
Department of Methodology, London School of Economics and Political Science
Dr Ben Wilson
Intermediate (some prior knowledge)
The lecture will begin with an overview of event history models, as used in many social science disciplines. The lecture will show how these models can be used to analyse the ‘duration until an event occurs’ (sometimes referred to as ‘survival time’). It will explain how event history models allow researchers to estimate the probability (or risk) of an event occurring, even when data are ‘censored’ (e.g. when there is missing data due to attrition or study drop-out). For the analysis of individual-level data, these methods can be used to investigate a wide range of events, including migration, divorce, and unemployment. In addition, the same models can be used to analyse events for different types of unit, including firms, cities or governments.
After providing an overview of event history models, the rest of the lecture will focus on discrete-time event history models. These models measure time in ‘discrete units’ such as months or years, which is typically the same unit of time that is used when event data are collected. Discrete-time models have many other advantages, including the fact that they can easily incorporate time-varying covariates. They can also be extended to allow a variety of advanced applications, including the analysis of repeated events, or models that allow for unobserved heterogeneity. All of these terms will be explained in the lecture, which will aim to provide the audience with a solid introduction to the most salient issues for applied research.
Website and registration:
Event History Analysis
Related publications and presentations: