A note on the maximum likehood estimation of allocation systems
โ Scribed by Philippe J. Deschamps
- Publisher
- Elsevier Science
- Year
- 1988
- Tongue
- English
- Weight
- 240 KB
- Volume
- 6
- Category
- Article
- ISSN
- 0167-9473
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
In estimating a bounded normal mean, it is known that the maximum likelihood estimator is inadmissible for squared error loss function. In this paper, we discuss the admissibility for other loss functions. We prove that the maximum likelihood estimator is admissible under absolute error loss.
We show that a non-identifiability problem can occur when one attempts to estimate the degrees of freedom and the unstructured covariance matrix simultaneously in a Gaussian-inverted Wishart model, using the maximum likelihood approach. However, the EM algorithm may falsely converge to give finite e