|
Activity Number:
|
254
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Teaching Statistics in the Health Sciences
|
| Abstract - #309679 |
|
Title:
|
The Effect of Effect Size on Teaching, Collaboration, and Publishing
|
|
Author(s):
|
Linda S. Hynan*+ and Alan Elliott
|
|
Companies:
|
The University of Texas Southwestern Medical Center at Dallas and The University of Texas Southwestern Medical Center at Dallas
|
|
Address:
|
Division of Biostatistics, Dallas, TX, 75390,
|
|
Keywords:
|
Effect Size ; p-values ; hypothesis testing
|
|
Abstract:
|
Statistical significance testing has been an essential tool of researchers for decades. Hypothesis testing provides a way to remove personal bias from the decision-making process. However, overconfidence in decisions based on p-values less than 0.05 has undoubtedly led to many erroneous conclusions. The rampant use of tests on the same data set guarantees that incorrect decisions are made. Furthermore, a strict interpretation of significance testing without regard to scientific importance leads to missed opportunities for scientific advancement and may result, for example, in the implementation of an ineffective medical procedure or the abandonment of a line of research that could have proven valuable. This paper reviews the pros and cons of reliance on p-values and how APA guidelines that recommend reporting effect sizes could change how results are presented in scientific journals.
|
