A sensitivity analysis for causal parameters in structural proportional hazards models.

Els Goetghebeur; Tom Loeys

SORT (2003)

  • Volume: 27, Issue: 1, page 31-40
  • ISSN: 1696-2281

Abstract

top
Deviations from assigned treatment occur often in clinical trials. In such a setting, the traditional intent-to-treat analysis does not measure biological efficacy but rather programmatic effectiveness. For all-or-nothing compliance situation, Loeys and Goetghebeur (2003) recently proposed a Structural Proportional Hazards method. It allows for casual estimation in the complier subpopulation provided the exclusion restriction holds: randomization per se has no effect unless exposure has changed. The asumption is typically made with structural models for noncompliance but questioned when the trial is not blinded. In this paper we extend the structural PH model to allow for an effect of randomization per se. This enables analyzing sensitivity of conclusions to deviations from the exclusion restriction. In a colo-rectal cancer trial we find the causal estimator for the effect of an arterial device implantation to be remarkably insensitive to such deviations.

How to cite

top

Goetghebeur, Els, and Loeys, Tom. "A sensitivity analysis for causal parameters in structural proportional hazards models.." SORT 27.1 (2003): 31-40. <http://eudml.org/doc/40436>.

@article{Goetghebeur2003,
abstract = {Deviations from assigned treatment occur often in clinical trials. In such a setting, the traditional intent-to-treat analysis does not measure biological efficacy but rather programmatic effectiveness. For all-or-nothing compliance situation, Loeys and Goetghebeur (2003) recently proposed a Structural Proportional Hazards method. It allows for casual estimation in the complier subpopulation provided the exclusion restriction holds: randomization per se has no effect unless exposure has changed. The asumption is typically made with structural models for noncompliance but questioned when the trial is not blinded. In this paper we extend the structural PH model to allow for an effect of randomization per se. This enables analyzing sensitivity of conclusions to deviations from the exclusion restriction. In a colo-rectal cancer trial we find the causal estimator for the effect of an arterial device implantation to be remarkably insensitive to such deviations.},
author = {Goetghebeur, Els, Loeys, Tom},
journal = {SORT},
keywords = {Ensayo clínico; Bioestadística; Análisis de supervivencia; Estimación; Inferencia causal; Análisis de datos censurados; Análisis de sensibilidad; causal inference; compliance; exclusion restriction; randomized clinical trials},
language = {eng},
number = {1},
pages = {31-40},
title = {A sensitivity analysis for causal parameters in structural proportional hazards models.},
url = {http://eudml.org/doc/40436},
volume = {27},
year = {2003},
}

TY - JOUR
AU - Goetghebeur, Els
AU - Loeys, Tom
TI - A sensitivity analysis for causal parameters in structural proportional hazards models.
JO - SORT
PY - 2003
VL - 27
IS - 1
SP - 31
EP - 40
AB - Deviations from assigned treatment occur often in clinical trials. In such a setting, the traditional intent-to-treat analysis does not measure biological efficacy but rather programmatic effectiveness. For all-or-nothing compliance situation, Loeys and Goetghebeur (2003) recently proposed a Structural Proportional Hazards method. It allows for casual estimation in the complier subpopulation provided the exclusion restriction holds: randomization per se has no effect unless exposure has changed. The asumption is typically made with structural models for noncompliance but questioned when the trial is not blinded. In this paper we extend the structural PH model to allow for an effect of randomization per se. This enables analyzing sensitivity of conclusions to deviations from the exclusion restriction. In a colo-rectal cancer trial we find the causal estimator for the effect of an arterial device implantation to be remarkably insensitive to such deviations.
LA - eng
KW - Ensayo clínico; Bioestadística; Análisis de supervivencia; Estimación; Inferencia causal; Análisis de datos censurados; Análisis de sensibilidad; causal inference; compliance; exclusion restriction; randomized clinical trials
UR - http://eudml.org/doc/40436
ER -

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.