University of Illinois Urbana-Champaign

"Sequential analysis of duration data with application to ""reemployment bonus"" experiments"

Bilias, Yannis

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/22378

Description

Title
"Sequential analysis of duration data with application to ""reemployment bonus"" experiments"
Author(s)
Bilias, Yannis
Issue Date
1995
Doctoral Committee Chair(s)
Koenker, Roger W.
Department of Study
Economics
Discipline
Economics
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
  • Statistics
  • Economics, Labor
  • Economics, Theory
Language
eng
Abstract
  • "Suitable methodology and an asymptotic theory for the sequential analysis of time-to-event (duration) data is developed and its application in ""Reemployment Bonus"" experiments is studied."
  • First, a proportional hazards regression model with possibly censored observations, time-dependent covariates and staggered entry is assumed. Sequential analysis of the partial likelihood score process and other related statistics cannot rely on martingale theory. Instead a modern empirical process theory is used to deal with the underlying two-dimensional character of the problem. A very general treatment of the large sample theory with minimum technicalities is made developed.
  • "Next, sequential testing procedures for the analysis of duration data are employed to reconsider the Pennsylvania ""Reemployment Bonus"" Demonstration. The efficiency and flexibility gained by the monitoring of large-scale experiments is illustrated. Boundaries that preserve the overall type-I error are constructed based on the asymptotic theory developed previously. Several treatments show their efficacy earlier than the termination day dictated by the fixed-sample design. Stopping the study at that time would have achieved important pecuniary savings."
  • Last, techniques developed earlier are applied to test statistics arising from the analysis of right-truncated data in which both the duration and calendar time are naturally involved. Asymptotic theory for the one-sample and the regression problems is established.
Type of Resource
text
Permalink
http://hdl.handle.net/2142/22378
Copyright and License Information
Copyright 1995 Bilias, Yannis

Owning Collections

Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois
Dissertations and Theses - Economics