ebook img

On improving the forecast accuracy of the hidden Markov model PDF

130 Pages·2016·1.33 MB·English
by  
Save to my drive
Quick download
Download
Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.

Preview On improving the forecast accuracy of the hidden Markov model

n w o On improving the foTrecast e accuracy of the hiddpen Markov a C model f o y Thomas Rooney t i s r Dissertation submitteed in partial fulfilment of the requirements for the v degree of Master of Commerce i n in U The Faculty of Commerce Department of Actuarial Science January 2016 The financial assistance of the National Research Foundation (NRF) towards this research is hereby acknowledged. Opinions expressed and conclusions arrived at are those of the author and are not necessarily to be attributed to the NRF. n w The copyright of this thesis vests in the author. No o T quotation from it or information derived from it is to be published without full acknowledgeement of the source. p The thesis is to be used for private study or non- a C commercial research purposes only. f o Published by the Universit y of Cape Town (UCT) in terms y t of the non-exclusive license granted to UCT by the author. i s r e v i n U 2 Declaration I, Thomas Jeffrey Amhurst Rooney, hereby declare that the work on which thisdissertationisbasedismyoriginalwork(exceptwhereacknowledgements indicate otherwise) and that neither the whole work nor any part of it has been, is being or is to be submitted for another degree in this or any other University. I empower the University of Cape Town to reproduce for the purpose of research either the whole or any portion of the contents in any manner whatsoever. 15 November 2016 Signature removed TJA Rooney Date Abstract The forecast accuracy of a hidden Markov model (HMM) may be low due first, to the measure of forecast accuracy being ignored in the parameter- estimation method and, second, to overfitting caused by the large number of parameters that must be estimated. A general approach to forecasting is described which aims to resolve these two problems and so improve the forecast accuracy of the HMM. First, the application of extremum estimators to the HMM is proposed. Extremum estimators aim to improve the forecast accuracy of the HMM by minimising an estimate of the forecast error on the observed data. The forecast accuracy is measured by a score function and the use of some general classes of score functions is proposed. This approach contrasts with the standard use of a minus log-likelihood score function. Second, penalised estimation for the HMM is described. The aim of penalised estimation is to reduce overfitting and so increase the forecast accuracy of the HMM. Penalties on both the state-dependent distribution parameters and transition probability matrix areproposed. Inaddition, anumberofcross-validationapproachesfortuning the penalty function are investigated. Empirical assessment of the proposed approach on both simulated and real data demonstrated that, in terms of forecast accuracy, penalised HMMs fittedusingextremumestimatorsgenerallyoutperformedunpenalisedHMMs fitted using maximum likelihood. i Acknowledgements Firstly, I would like express my sincere gratitude to my supervisor, Asso- ciate Professor Iain L. MacDonald for his guidance, support, patience and motivation for this dissertation. Iwouldalsoliketothankmyparentsfortheirunconditionalsupportboth generally and, in particular, throughout writing this dissertation. The financial assistance of the National Research Foundation (NRF) to- wards this research is hereby acknowledged. Opinions expressed and con- clusions arrived at are those of the author and are not necessarily to be attributed to the NRF. iii Contents Abstract i Acknowledgements iii Notation and abbreviations viii 1 Introduction 1 2 Introduction to hidden Markov models 3 2.1 The basic HMM . . . . . . . . . . . . . . . . . . . . . . . . . . 3 2.2 Likelihood functions and forecast distributions . . . . . . . . . 5 3 Forecasting and extremum estimators 7 3.1 The basic forecasting approach . . . . . . . . . . . . . . . . . 8 3.2 Extremum estimators for the HMM . . . . . . . . . . . . . . . 9 3.3 Consistency of extremum estimators . . . . . . . . . . . . . . 11 3.4 Model checking and measuring uncertainty of a forecast . . . . 11 3.4.1 Checking a forecasting model with pseudo-residuals . . 12 3.4.2 Forecast intervals and potential risk . . . . . . . . . . . 13 4 Two general forms of score functions 16 4.1 The minus log-likelihood score function . . . . . . . . . . . . . 16 4.2 Point-forecast based score functions . . . . . . . . . . . . . . . 17 4.2.1 Pairwise loss functions and optimal point predictors . . 18 v

Description:
On improving the forecast accuracy of the hidden Markov model. Thomas Rooney. Dissertation submitted in partial fulfilment of the requirements for the application of extremum estimators to the HMM is proposed. To assess the adequacy of a forecast model, use is made of forecast pseudo-.
See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.