JSM 2013 Home
Online Program Home
My Program

Abstract Details

Activity Number: 149
Type: Invited
Date/Time: Monday, August 5, 2013 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract - #310484
Title: Instrumental variable estimation with binary outcomes can lead to lack of identification with weak instruments
Author(s): Stephen Burgess*+
Companies: University of Cambridge
Keywords:
Abstract:

A parameter in a statistical model is identified if an estimate of its value can be uniquely determined on the basis of the data. For an instrumental variable analysis with a binary outcome in which estimating equations are used to obtain the optimal parameter values, the causal parameter of interest may not be identified. This occurs when the estimating equations are satisfied for no values of the parameter, or for multiple values of the parameter. Many estimation methods make use of estimating equations, such as the semi-parametric generalized method of moments and structural mean model frameworks. In this talk, we demonstrate that lack of identification can occur when using either of these frameworks for parameter estimation, especially if the instrument is weak. In a practical setting, the reported estimates and standard errors from an automated optimization routine may be misleading. We investigate the relationship between the strength of the instrument and the proportion of simulated datasets for which there is a unique solution of the optimization criteria. We see that, for instruments which do not explain much of the variance in the exposure ($\rho^2 \le 0.005$), this proportion does not appear to depend on the sample size.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2013 program




2013 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

ASA Meetings Department  •  732 North Washington Street, Alexandria, VA 22314  •  (703) 684-1221  •  meetings@amstat.org
Copyright © American Statistical Association.