The Annals of Statistics

Conditional Exponential Families and a Representation Theorem for Asympotic Inference

Paul D. Feigin

Full-text: Open access

Abstract

Conditional exponential families of Markov processes are defined and a representation of the score function martingale is established for the important conditionally additive case. This result unifies those obtained separately for different examples and provides the key to asymptotic normality results for the maximum likelihood estimate.

Article information

Source
Ann. Statist., Volume 9, Number 3 (1981), 597-603.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176345463

Digital Object Identifier
doi:10.1214/aos/1176345463

Mathematical Reviews number (MathSciNet)
MR615435

Zentralblatt MATH identifier
0476.62070

JSTOR
links.jstor.org

Subjects
Primary: 62M05: Markov processes: estimation
Secondary: 60J30

Keywords
Conditionally additive exponential family nonergodic stochastic processes additive processes

Citation

Feigin, Paul D. Conditional Exponential Families and a Representation Theorem for Asympotic Inference. Ann. Statist. 9 (1981), no. 3, 597--603. doi:10.1214/aos/1176345463. https://projecteuclid.org/euclid.aos/1176345463


Export citation