Event History And Duration Modeling Essay ⋆ Political Science Essay Examples ⋆ EssayEmpire

This example Event History And Duration Modeling Essay is published for educational and informational purposes only. If you need a custom essay or research paper on this topic please use our writing services. EssayEmpire.com offers reliable custom essay writing services that can help you to receive high grades and impress your professors with the quality of each essay or research paper you hand in.

Event history analysis is a statistical technique that assesses the risk of an event’s occurring. An event is a change from one state to another, for example, death, entry of a challenger in an election, confirmation of a judicial nominee, or the onset of war. The dependent variable is the time until the event occurs; the model considers both whether and when an event occurs. This technique is also referred to as duration, survival, or reliability analysis.

Event history models manage problems common to longitudinal data, such as censored observations and time varying covariates. Censoring occurs when information about an observation is incomplete, such as when an observation has not experienced an event before the data collection process ends. Time-varying covariates take on different values over time for a single observation.

Parametric models assume that the time until an event occurs follows a specific distribution. The semi parametric Cox model is more appropriate when the primary objective is to understand the impact of covariates on the risk of an event and is the most commonly used model in event history analysis. Semi parametric models do not specify a distributional shape for the timing of events but are parameterized by the explanatory variables.

Key concepts for estimating and understanding the event history models are the hazard rate, risk set, failure rate, and survival function. A hazard rate is the probability that an event will occur for a particular observation at a particular time. The risk set includes all of the observations that are still at risk for experiencing the event. Once an event occurs, the observation is incorporated into the failure rate. All observations that have not failed are included in the survival function. The hazard rate is the proportion of the failure rate to the survival function.

Diagnostic tests should be used in event history analysis and include diagnostics to test for outliers, influence, adequacy of the model, linearity in the covariates, and proportional hazards. If the proportional hazards assumption holds, the hazard rate will be the same at the first time period under study as it is at the last period under study. There are numerous substantive reasons one may not expect the assumption of proportional effects to hold, such as learning. To correct for nonproportionality, the offending covariate is interacted with some function of time.

Advanced event history models incorporate ordered multiple events (repeated events model) and unordered multiple events (competing risks model). In repeated events data, dependence is possible when an event is conditional on another event’s having occurred or the result of correlation in repeated processes. The conditional frailty model can handle both types of dependence.

Bibliography:

Blossfeld, Hans-Peter, and Gotz Rohwer. Techniques of Event History Modeling. 2d ed. London: Lawrence Erlbaum, 2002.
Box-Steffensmeier, Janet, and Bradford Jones. Event History Modeling. Cambridge: Cambridge University Press, 2004.
Klein, John P., and Melvin L. Moeschberger. Survival Analysis:Techniques for Censored and Truncated Data. New York: Springer-Verlag, 1997.
Singer, Judith D., and John B.Willett. Applied Longitudinal Data Analysis: Modeling Change and Event Occurrence. Oxford, UK: Oxford University Press, 2003.
Therneau,Terry M., and Patricia Grambsch. Modeling Survival Data: Extending the Cox Model. New York: Springer-Verlag, 2000.