Far East Journal of Theoretical Statistics
Volume 20, Issue 2, Pages 217 - 240
(November 2006)
|
|
MAXIMUM LIKELIHOOD ESTIMATORS FOR NORMAL AND GAMMA MIXTURES
K. O. Bowman (U. S. A.) and L. R. Shenton (U. S. A.)
|
Abstract: First of all we consider iterative schemes to discover
solutions for maximum likelihood estimators for normal mixtures, and gamma
mixtures. From our examples, the iterative scheme works well for the normal, but
poorly for the gamma mixtures. Second, we set up short tabulations of the low
order asymptotic moments (bias, variances to order
and skewness to order
N being the sample size). These moments are derived from a Maple code
interpretation due to Bowman and Shenton (Bias, variance, skewness and kurtosis
of maximum likelihood estimators using Maple, Far East J. Theo. Stat. 17(2)
(2005), 137-195). In conclusion this paper supplies further evidence for the
correctness of the Maple code. |
Keywords and phrases: asymptotic skewness, asymptotic variance, iterative schemes |
|
Number of Downloads: 270 | Number of Views: 559 |
|