Title: Hidden-Markov Models for Count Time Series
Authors: Weiß, Christian H. 
Language: en
Issue Date: 2018
Document Type: Article
Source: Enthalten in: Wiley StatsRef, April 2014- . - 2018, insges. 5 S.
Journal / Series / Working Paper (HSU): Wiley StatsRef 
Volume: 2018
Pages: 5
Hidden-Markov models are a type of parameterdriven statespace model, which can be used for modeling count time series. Their observations stem from a finite mixture of count distributions and exhibit a nonMarkovian dependence structure. The likelihood function and forecasting distributions can be computed efficiently, and a simple algorithm is available for a global decoding of the hidden states.
Organization Units (connected with the publication): Quantitative Methoden der Wirtschaftswissenschaften 
URL: https://ub.hsu-hh.de/DB=1.8/XMLPRS=N/PPN?PPN=1031846697
DOI: 10.1002/9781118445112.stat08135
Appears in Collections:2018

Show full item record

CORE Recommender

Google ScholarTM




Items in openHSU are protected by copyright, with all rights reserved, unless otherwise indicated.