
Questa tesi riguarda i modelli strutturali per le serie storiche conosciuti come modelli State Space. I modelli strutturali per le serie storiche sono una classe di modelli parametrici che si basano sulle componenti latenti. Il loro compito è di modellare le principali caratteristiche di una serie storica come per esempio il trend, ciclo economico e stagionalità. La tesi è divisa in tre parti : la prima parte (capitolo 2) riguarda i modelli a voltatilità stocastica, la seconda parte (capitolo 3) riguarda i modelli fattoriali e la terza ed ultima parte (capitolo 4) tratta la selezione di modelli in ambito Bayesiano. Una introduzione alla metodologia State Space è presente al capitolo 1.
This dissertation deals with structural time series models. Structural time series models refer to a class of parametric models that are specified directly in terms of unobserved components which capture essential features of the series, such as trend, cycle and seasonality. This dissertation is divided into three main parts: the first (chapter 2) deals with stochastic volatility models, the second (chapter 3) deals with dynamic factor models and the third (chapter 4) deals with Bayesian model selection. A general introduction to the state space methodology is provided in chapter 1.
sequential importance sampling, state space model, 330, state space models; Bayesian model selection; dynamic factor models; maximum likelihood; sequential importance sampling; Bayesian estimation, Settore SECS-P/05 - ECONOMETRIA, Bayesian model selection, dynamic factor model, Settore ECON-05/A - Econometria, maximum likelihood, Bayesian estimation
sequential importance sampling, state space model, 330, state space models; Bayesian model selection; dynamic factor models; maximum likelihood; sequential importance sampling; Bayesian estimation, Settore SECS-P/05 - ECONOMETRIA, Bayesian model selection, dynamic factor model, Settore ECON-05/A - Econometria, maximum likelihood, Bayesian estimation
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
