|
Activity Number:
|
75
- Contributed Poster Presentations: Biometrics Section
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2020 : 10:00 AM to 2:00 PM
|
|
Sponsor:
|
Biometrics Section
|
|
Abstract #313055
|
|
|
Title:
|
Arctangent Augmented Square Root Transformation
|
|
Author(s):
|
Mitchell J Rosen*
|
|
Companies:
|
Covance, Inc.
|
|
Keywords:
|
variance stabilizing transformation;
square root transformation
|
|
Abstract:
|
The square root transformation is well-known variance-stabilizing transformation for Poisson data. Variations of the square root, including Tukey-Freeman and Anscombe, are ineffective when the Poisson mean is less than unity. This paper proposes a family of arctangent-augmented square root transformations that converges to the same asymptotic variance as the square root. Parameters can be obtained using standard maximum likelihood methods. Computer simulations demonstrate that variance stabilization is achieved when the Poisson mean is >=0.5. A proof of convergence to the asymptotic variance is also provided.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2020 program
|
