EM algorithm for Markov chains observed via Gaussian noise and point process information: theory and case studies

DOI10.1515/strm-2017-0021zbMath1387.60072OpenAlexW2734737420MaRDI QIDQ1688729

Zehra Eksi, Rüdiger Frey, Camilla Damian

Publication date: 11 January 2018

Published in: Statistics \& Risk Modeling (Search for Journal in Brave)

Full work available at URL: http://epub.wu.ac.at/6952/1/damian%2Deksi%2Dfrey%2Dstatistics%2Dand%2Drisk%2Dmodelling.pdf

zbMATH Keywords

nonlinear filteringpoint processesgoodness-of-fit testshidden Markov modelsexpectation maximization algorithmcredit risk ratings

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Applications of statistics to actuarial sciences and financial mathematics (62P05) Signal detection and filtering (aspects of stochastic processes) (60G35) Credit risk (91G40)

Related Items (5)

Statistical inference for partially observed Markov-modulated diffusion risk model ⋮ Stochastic filtering of a pure jump process with predictable jumps and path-dependent local characteristics ⋮ RATING TRANSITIONS FORECASTING: A FILTERING APPROACH ⋮ Optimal liquidation under partial information with price impact ⋮ Optimal convergence trading with unobservable pricing errors

Uses Software

• QRM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Hidden Markov models in finance
• Parameter estimation of partially observed continuous time stochastic processes via the EM algorithm
• Point processes and queues. Martingale dynamics
• Pricing and hedging of credit derivatives via the innovations approach to nonlinear filtering
• Optimizing the terminal wealth under partial information: the drift process as a continuous time Markov chain
• Cramér-Lundberg approximations for ruin probabilities of risk processes perturbed by diffusion
• Hidden Markov models in finance. Further developments and applications. Volume II
• A hidden Markov model of credit quality
• A NONLINEAR FILTERING APPROACH TO VOLATILITY ESTIMATION WITH A VIEW TOWARDS HIGH FREQUENCY DATA
• New finite-dimensional filters and smoothers for noisily observed Markov chains
• Risk theory in a Markovian environment
• Time discretization of continuous-time filters and smoothers for HMM parameter estimation
• Discrete-Time Expectation Maximization Algorithms for Markov-Modulated Poisson Processes
• Portfolio optimization with unobservable Markov-modulated drift process

This page was built for publication: EM algorithm for Markov chains observed via Gaussian noise and point process information: theory and case studies