Contents

My thesis on Time Varying Parameter Models for Inflation and Exchange Rates contains the chapters as specified below.

Courtesy of the publishers of the papers underlying chapters 2 and 3, the thesis is available through the WebDOC system of the Econometric Institute as a PDF document (1.5MB).

Acknowledgements
1Introduction
1.1Motivation
1.2Inflation: Long memory
1.3Exchange rate: Varying trend and variance
1.4Overview
2Long Memory and Level Shifts: Re-Analysing Inflation Rates
2.1Introduction
2.2A motivation
2.3Some theoretical results
2.4Simulation evidence
2.5Inflation: Long memory and level shifts
2.6Conclusions
2.ACalculating the likelihood and the test statistics
2.BGenerating an ARFIMA process
2.CData sources, programs, justifications
3Inflation, Forecast Intervals and Long Memory Regression Models
3.1Introduction
3.2Recursive ARFIMAX forecasting
3.2.1Basic features of U.S. core inflation
3.2.2ARFIMAX modelling
3.2.3Recursive estimation and forecasting
3.2.4Recursive estimates
3.2.5Recursive forecasting
3.3Recursive weighted ARFIMAX forecasting
3.4Recursive ARFIMAX forecast tests
3.5Conclusion
4Bayesian Sampling Methods
4.1Introduction
4.2Basic sampling methods
4.2.1Importance sampling
4.2.2Sampling/Importance Resampling
4.2.3Acceptance-rejection sampling
4.2.4The Metropolis-Hastings algorithm
4.2.5Gibbs sampling
4.2.6On convergence: Theory
4.2.7On convergence: Practice
4.3Extensions
4.3.1Metropolis-within-Gibbs
4.3.2Multistep Gibbs samplers revisited
4.3.3Griddy Gibbs sampler
4.3.4Adaptive Polar Sampling
4.4Posterior odds and marginal likelihood
4.4.1Posterior odds, the Bayes factor, and model choice
4.4.2Calculating the marginal likelihood
4.4.3Calculating the Bayes factor
4.5Example: Sampling from a time series model
4.5.1Introducing the model
4.5.2Likelihood and posterior
4.5.3Sampling methods based on the likelihood function
4.5.4Sampling methods based on the conditional densities
4.5.5Calculating the marginal likelihood of the model
4.5.6Sampling setup and details
4.6Concluding remarks
4.ASampling and the state space model
4.BDerivations and distributions for APS
4.CSelected density functions
5Daily Hedging of Currency Risk
5.1Introduction
5.2Currency hedging
5.3Time series models for exchange rate returns
5.4Bayesian inference and decision
5.4.1Prior structure
5.4.2Constructing a posterior sample
5.4.3Evaluating the marginal likelihood
5.4.4Predictive analysis
5.4.5Decision analysis
5.5Exchange rate data and the interest rate
5.5.1Stylized facts
5.5.2Data in the evaluation period
5.6Convergence of MCMC and posterior results
5.6.1The posterior distribution
5.6.2Marginal likelihood
5.6.3Predictive density of the models
5.7Hedging results
5.7.1On the setup
5.7.2Naive hedging strategies
5.7.3Variability of the hedging decision
5.7.4Returns and utilities of model-based strategies
5.7.5Value-at-Risk and the Sharpe ratio
5.7.6Other viewpoints on the results
5.8Concluding remarks
5.AGibbs sampling with data augmentation
6Conclusions
6.1General remarks
6.2Inflation rates
6.3Bayesian simulation methods
6.4Hedging currency risk
Bibliography
Nederlandse samenvatting


File translated from TEX by TTH, version 3.03. On 12 Dec 2001, 20:14.


[Main page] [Top] [Next: Bibliography]
Last change: 9/12/2001