Title :
Consistency and identifiability of autoregressive models with Markov regime
Author :
Krishnamurthy, Vikram ; Ryden, Tobias
Author_Institution :
Dept. of Electr. Eng., Melbourne Univ., Parkville, Vic., Australia
Abstract :
An autoregressive process with Markov regime is an autoregressive process for which the regression function at each time-point is given by a (nonobservable) Markov chain. We show consistency of a conditional maximum likelihood estimation and discuss identifiability of such models
Keywords :
Markov processes; autoregressive processes; identification; maximum likelihood estimation; Markov regime; autoregressive model consistency; autoregressive model identifiability; conditional maximum likelihood estimation; nonobservable Markov chain; regression function; Autoregressive processes; Communication networks; Ear; Hidden Markov models; Maximum likelihood detection; Maximum likelihood estimation; Physiology; Random variables; Recursive estimation; Speech recognition;
Conference_Titel :
Information, Decision and Control, 1999. IDC 99. Proceedings. 1999
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-5256-4
DOI :
10.1109/IDC.1999.754164
