Search results for "Autoregressive model"
showing 10 items of 120 documents
Conditional particle filters with diffuse initial distributions
2020
Conditional particle filters (CPFs) are powerful smoothing algorithms for general nonlinear/non-Gaussian hidden Markov models. However, CPFs can be inefficient or difficult to apply with diffuse initial distributions, which are common in statistical applications. We propose a simple but generally applicable auxiliary variable method, which can be used together with the CPF in order to perform efficient inference with diffuse initial distributions. The method only requires simulatable Markov transitions that are reversible with respect to the initial distribution, which can be improper. We focus in particular on random-walk type transitions which are reversible with respect to a uniform init…
An ensemble approach to short-term forecast of COVID-19 intensive care occupancy in Italian Regions
2020
Abstract The availability of intensive care beds during the COVID‐19 epidemic is crucial to guarantee the best possible treatment to severely affected patients. In this work we show a simple strategy for short‐term prediction of COVID‐19 intensive care unit (ICU) beds, that has proved very effective during the Italian outbreak in February to May 2020. Our approach is based on an optimal ensemble of two simple methods: a generalized linear mixed regression model, which pools information over different areas, and an area‐specific nonstationary integer autoregressive methodology. Optimal weights are estimated using a leave‐last‐out rationale. The approach has been set up and validated during t…
Factorial graphical models for dynamic networks
2015
AbstractDynamic network models describe many important scientific processes, from cell biology and epidemiology to sociology and finance. Estimating dynamic networks from noisy time series data is a difficult task since the number of components involved in the system is very large. As a result, the number of parameters to be estimated is typically larger than the number of observations. However, a characteristic of many real life networks is that they are sparse. For example, the molecular structure of genes make interactions with other components a highly-structured and, therefore, a sparse process. Until now, the literature has focused on static networks, which lack specific temporal inte…
A Novel Approach to Propagation Pattern Analysis in Intracardiac Atrial Fibrillation Signals
2010
The purpose of this study is to investigate propagation patterns in intracardiac signals recorded during atrial fibrillation (AF) using an approach based on partial directed coherence (PDC), which evaluates directional coupling between multiple signals in the frequency domain. The PDC is evaluated at the dominant frequency of AF signals and tested for significance using a surrogate data procedure specifically designed to assess causality. For significantly coupled sites, the approach allows also to estimate the delay in propagation. The methods potential is illustrated with two simulation scenarios based on a detailed ionic model of the human atrial myocyte as well as with real data recordi…
A new Frequency Domain Measure of Causality based on Partial Spectral Decomposition of Autoregressive Processes and its Application to Cardiovascular…
2019
We present a new method to quantify in the frequency domain the strength of directed interactions between linear stochastic processes. This issue is traditionally addressed by the directed coherence (DC), a popular causality measure derived from the spectral representation of vector autoregressive (AR) processes. Here, to overcome intrinsic limitations of the DC when it needs to be objectively quantified within specific frequency bands, we propose an approach based on spectral decomposition, which allows to isolate oscillatory components related to the pole representation of the vector AR process in the Z-domain. Relating the causal and non-causal power content of these components we obtain…
The Nexus between Sovereign CDS and Stock Market Volatility: New Evidence
2021
This paper extends the studies published to date by performing an analysis of the causal relationships between sovereign CDS spreads and the estimated conditional volatility of stock indices. This estimation is performed using a vector autoregressive model (VAR) and dynamically applying the Granger causality test. The conditional volatility of the stock market has been obtained through various univariate GARCH models. This methodology allows us to study the information transmissions, both unidirectional and bidirectional, that occur between CDS spreads and stock volatility between 2004 and 2020. We conclude that CDS spread returns cause (in the Granger sense) conditional stock volatility, m…
Improved Frequentist Prediction Intervals for Autoregressive Models by Simulation
2015
It is well known that the so called plug-in prediction intervals for autoregressive processes, with Gaussian disturbances, are too narrow, i.e. the coverage probabilities fall below the nominal ones. However, simulation experiments show that the formulas borrowed from the ordinary linear regression theory yield one-step prediction intervals, which have coverage probabilities very close to what is claimed. From a Bayesian point of view the resulting intervals are posterior predictive intervals when uniform priors are assumed for both autoregressive coefficients and logarithm of the disturbance variance. This finding opens the path how to treat multi-step prediction intervals which are obtain…
A framework for assessing frequency domain causality in physiological time series with instantaneous effects.
2013
We present an approach for the quantification of directional relations in multiple time series exhibiting significant zero-lag interactions. To overcome the limitations of the traditional multivariate autoregressive (MVAR) modelling of multiple series, we introduce an extended MVAR (eMVAR) framework allowing either exclusive consideration of time-lagged effects according to the classic notion of Granger causality, or consideration of combined instantaneous and lagged effects according to an extended causality definition. The spectral representation of the eMVAR model is exploited to derive novel frequency domain causality measures that generalize to the case of instantaneous effects the kno…
Spatial econometrics and the hedonic pricing model: what about the temporal dimension
2014
Recent ready access to free software and toolbox applications is directly impacting spatial econometric modelling when working with geolocated data. Spatial econometric models are valuable tools for taking into account the possible latent structure of the price determination process and ensuring that the coefficients estimated are unbiased and efficient. However, mechanical applications can potentially bias estimated coefficients if spatial data is pooled over time because the applications consider the spatial dimension alone. Spatial models neglect the fact that data (e.g. real estate) may consist of a collection of spatial data pooled over time, and that time relations generate a unidirec…
Stochastic dynamical modelling of spot freight rates
2014
Based on empirical analysis of the Capesize and Panamax indices, we propose different continuous-time stochastic processes to model their dynamics. The models go beyond the standard geometric Brownian motion, and incorporate observed effects like heavy-tailed returns, stochastic volatility and memory. In particular, we suggest stochastic dynamics based on exponential Levy processes with normal inverse Gaussian distributed logarithmic returns. The Barndorff-Nielsen and Shephard stochastic volatility model is shown to capture time-varying volatility in the data. Finally, continuous-time autoregressive processes provide a class of models sufficiently rich to incorporate short-term persistence …