 |
|
Using Observational Data to Estimate Treatment Effects
|
|
| Since this article does not have an abstract, we have provided the first 150 words of the full text and any section headings. |
|
|
|
To the Editor: We would like to respond to some points raised by Drs D’Agostino and D’Agostino1 in their Editorial that accompanied our study.2
First, our claim that our instrumental variable estimates are unbiased and approximate the average effects from randomized controlled trials (RCTs) is based on the instrumental variable being valid and highly predictive of regional cardiac catheterization rates (29%-83%).3 To be valid, an instrumental variable must have no effect on outcomes other than through its effect on treatment.4 Our instrumental variable (regional cardiac catheterization rate) was unrelated to measured patient health status. Any effect on mortality was through health system factors related to cardiac catheterization, such as higher-volume hospitals with specialized staff and equipment and coronary care units.
Second, we included variables in the propensity score that were confounders, related to both the treatment and outcome. We did not include regional cardiac catheterization rate because it was not . . . [Full Text of this Article]
Therese A. Stukel, PhD
stukel@ices.on.ca
Institute for Clinical Evaluative Sciences
Toronto, Ontario
Elliott S. Fisher, MD, MPH
Center for the Evaluative Clinical Sciences
Dartmouth Medical School
Hanover, NH
David E. Wennberg, MD, MPH
Center for Outcomes Research and Evaluation
Maine Medical Center
Portland
RELATED LETTER
Using Observational Data to Estimate Treatment Effects—Reply
Ralph B. D’Agostino, Jr and Ralph B. D’Agostino, Sr
JAMA. 2007;297(19):2079.
EXTRACT
| FULL TEXT
|
