Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Are Mortality Differences Detected by Administrative Data Reliable and Actionable?

Are Mortality Differences Detected by Administrative Data Reliable and Actionable? Editorials represent the opinions EDITORIAL of the authors and JAMA and not those of the American Medical Association. Are Mortality Differences Detected by Administrative Data Reliable and Actionable? include falsification end points ; ie, some control analyses John P. A. Ioannidis, MD, DSc can be conducted on associations or effects known to be null. If these null effects are found to have nominally significant DMINISTRATIVE DATA OFFER IMPRESSIVE AMOUNTS differences in the data set, then inferences about any de- of information that can be readily analyzed. How- tected differences should be made with extreme caution. ever, how credible are the results derived from Second, information in administrative data sets is spuri- Athese behemoth data sets? Moreover, how pru- ous by default. These data are never collected for research dent is it to translate those results into policy actions, and, purposes, and coded disease diagnoses can be subject to sub- if this is done, what should that translation path involve? 1 stantial noise. Joynt et al performed a careful sensitivity analy- In this issue of JAMA, Joynt and colleagues report the sis to account for possible miscoding of pneumonia, sep- results of an interesting analysis that exemplifies these chal- sis, http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png JAMA American Medical Association

Are Mortality Differences Detected by Administrative Data Reliable and Actionable?

Ioannidis, John P. A.
JAMA , Volume 309 (13) – Apr 3, 2013
Download PDF
2 pages

Loading next page...
 
/lp/american-medical-association/are-mortality-differences-detected-by-administrative-data-reliable-and-ePU2ViCJCy

References (13)

Publisher
American Medical Association
Copyright
Copyright 2013 American Medical Association. All Rights Reserved. Applicable FARS/DFARS Restrictions Apply to Government Use.
ISSN
0098-7484
eISSN
1538-3598
DOI
10.1001/jama.2013.3150
pmid
23549588
Publisher site
See Article on Publisher Site

Abstract

Editorials represent the opinions EDITORIAL of the authors and JAMA and not those of the American Medical Association. Are Mortality Differences Detected by Administrative Data Reliable and Actionable? include falsification end points ; ie, some control analyses John P. A. Ioannidis, MD, DSc can be conducted on associations or effects known to be null. If these null effects are found to have nominally significant DMINISTRATIVE DATA OFFER IMPRESSIVE AMOUNTS differences in the data set, then inferences about any de- of information that can be readily analyzed. How- tected differences should be made with extreme caution. ever, how credible are the results derived from Second, information in administrative data sets is spuri- Athese behemoth data sets? Moreover, how pru- ous by default. These data are never collected for research dent is it to translate those results into policy actions, and, purposes, and coded disease diagnoses can be subject to sub- if this is done, what should that translation path involve? 1 stantial noise. Joynt et al performed a careful sensitivity analy- In this issue of JAMA, Joynt and colleagues report the sis to account for possible miscoding of pneumonia, sep- results of an interesting analysis that exemplifies these chal- sis,

Journal

JAMA – American Medical Association

Published: Apr 3, 2013

There are no references for this article.