Inferences Concerning The Mean Of The Gamma Distribution

Abstract

Approximate tests for the mean of a gamma distribution with both parameters unknown are derived. The power of these tests is close to the power of the corresponding uniformly most powerful tests for the mean when the shape parameter is assumed known. The tests are studied by Monte Carlo simulation, and limiting results are also provided as the shape parameter goes to zero or infinity, as well as for the large-sample case. A limited study indicating the nonrobustness of the standard t test for this case is also included. © 1980, Taylor & Francis Group, LLC.

Department(s)

Mathematics and Statistics

Keywords and Phrases

Approximate tests; Gamma distribution; Maximum likelihood; Mean of the gamma distribution

International Standard Serial Number (ISSN)

1537-274X; 0162-1459

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2023 Taylor and Francis Group; Taylor and Francis; American Statistical Association, All rights reserved.

Publication Date

01 Jan 1980

Share

 
COinS