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

Learn More →

PValues vs Estimates of Association With Confidence Intervals

PValues vs Estimates of Association With Confidence Intervals COMMENTARY P Values vs Estimates of Association With Confidence Intervals INCE 1988, THE INTER- MISUSE OF P VALUES: ing them entirely or not using them national Committee of CLAIMS OF NO DIFFERENCE to interpret results. Medical Journal Edi- tors has used this lan- Authors sometimes use wording that P VALUES DO NOT MEASURE S guage in their guide- suggests that a large P value means STRENGTH OF ASSOCIATION lines for authors: “When possible, that there is no exposure-related dif- quantify findings and present them ference in the outcomes of the ob- If all else is equal, a P value will be with appropriate indicators of mea- served subjects and/or the unob- smaller when there is (1) a larger ob- served people in the population from served difference between 2 groups, surement error or uncertainty (such which study subjects were drawn. (2) a larger sample size, or (3) less as confidence intervals). Avoid re- Such wording confuses lack of a sta- variation within treatment group for lying solely on statistical hypoth- tistically significant difference with a continuous exposure or outcome esis testing, such as the use of P val- 4-12 4,13 lack of any difference. variable. P value size is http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png JAMA Pediatrics American Medical Association

PValues vs Estimates of Association With Confidence Intervals

JAMA Pediatrics , Volume 164 (2) – Feb 1, 2010

Loading next page...
 
/lp/american-medical-association/pvalues-vs-estimates-of-association-with-confidence-intervals-qwyE1404Ei
Publisher
American Medical Association
Copyright
Copyright 2010 American Medical Association. All Rights Reserved. Applicable FARS/DFARS Restrictions Apply to Government Use.
ISSN
2168-6203
eISSN
2168-6211
DOI
10.1001/archpediatrics.2009.266
pmid
20124150
Publisher site
See Article on Publisher Site

Abstract

COMMENTARY P Values vs Estimates of Association With Confidence Intervals INCE 1988, THE INTER- MISUSE OF P VALUES: ing them entirely or not using them national Committee of CLAIMS OF NO DIFFERENCE to interpret results. Medical Journal Edi- tors has used this lan- Authors sometimes use wording that P VALUES DO NOT MEASURE S guage in their guide- suggests that a large P value means STRENGTH OF ASSOCIATION lines for authors: “When possible, that there is no exposure-related dif- quantify findings and present them ference in the outcomes of the ob- If all else is equal, a P value will be with appropriate indicators of mea- served subjects and/or the unob- smaller when there is (1) a larger ob- served people in the population from served difference between 2 groups, surement error or uncertainty (such which study subjects were drawn. (2) a larger sample size, or (3) less as confidence intervals). Avoid re- Such wording confuses lack of a sta- variation within treatment group for lying solely on statistical hypoth- tistically significant difference with a continuous exposure or outcome esis testing, such as the use of P val- 4-12 4,13 lack of any difference. variable. P value size is

Journal

JAMA PediatricsAmerican Medical Association

Published: Feb 1, 2010

References