Moderate deviations of marginal maximum likelihood estimator for m-dependent processes.
- Resource Type
- Article
- Authors
- Chen, Ying-Xia; Miao, Yu
- Source
- Lithuanian Mathematical Journal. Oct2016, Vol. 56 Issue 4, p449-462. 14p.
- Subject
- *MAXIMUM likelihood statistics
*DEPENDENCE (Statistics)
*DEVIATION (Statistics)
*MATHEMATICAL models
*DISTRIBUTION (Probability theory)
- Language
- ISSN
- 0363-1672
We analyze the moderate deviations of the maximum likelihood estimator (MLE) derived under the assumption of independent identically distribution (i.i.d.) samples, where in the actual model the samples are m-dependent. The MLE under such a modeling mismatch are based on the marginal likelihood function, and it is referred to as marginal maximum likelihood estimator (MMLE). Under some regularity conditions, the moderate deviations of MMLE are obtained. Two common examples are studied. [ABSTRACT FROM AUTHOR]