A note on inference for the mean parameter of the gamma distribution
The two parameter gamma distribution with mean [mu] and shape [tau] is widely used in reliability and life data analysis. Unlike the normal distribution, which also has two parameters describing the location and the scale, inference for the mean parameter of the gamma distribution is much more complicated (Jensen, 1986) and consequently less well developed. In this paper, a method of averaging is proposed to obtain confidence intervals for the mean parameter of the gamma distribution at an arbitrary level of significance. Numerical examples showed that this method is not only simple but also very accurate.
| Year of publication: |
1993
|
|---|---|
| Authors: | Wong, Augustine C. M. |
| Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 17.1993, 1, p. 61-66
|
| Publisher: |
Elsevier |
| Keywords: | Confidence distribution function saddlepoint method Stirling formula |
Saved in:
Saved in favorites
Similar items by person
-
Comparisons of approximate tail probabilities for the shape parameter of the gamma distribution
Wong, Augustine C. M., (1998)
-
Numerical conversion of likelihood to significance
Wong, Augustine C. M., (1993)
- More ...