Activity Number:
|
413
- Consulting, Collaboration, Communication, and Impact
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 1, 2017 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Section on Statistical Consulting
|
Abstract #322889
|
View Presentation
|
Title:
|
Coping with Scientists' Culture in Statistical Consulting or Collaboration: Problems and Solutions
|
Author(s):
|
Martin Levy*
|
Companies:
|
University of Cincinnati
|
Keywords:
|
consulting ;
collaboration ;
beta hat method ;
gauge R&R ;
equivalence testing ;
MANOVA
|
Abstract:
|
Occasionally, a statistical collaborator proposes a statistical solution to a problem that meets with resistances or outright rejection. Assuming the statistician is fully educated on the scientific issues at hand, he/she has a few options. Drop the suggestion despite believing that it is correct and/or the most efficient method, and adopt a more understandable or elementary tack consistent with the prevailing culture while assuring that no underlying assumptions are violated. Endeavor to educate the scientists on the merits of the proposal. This may involve patient persuasion, citing an article on the proposed method in one of their own journals, or writing one if none exists. Lastly, withdraw from participation. I give four examples of resistance by scientific research colleagues to valid statistical proposals. One involves a method for conducting ANCOVA called the beta hat method. Another involves the suggestion of an experimental design protocol called Gauge R&R. A third involves the suggestion of equivalence testing. The last involves a suggestion of MANOVA. The scientists were either biomechanical engineers or orthopedic clinicians. I discuss the outcomes.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2017 program
|