Search

This paper presents a novel dynamic network autoregressive conditional heteroscedasticity (ARCH) model based on spatiotemporal ARCH models to forecast volatility in the US stock market. To improve the forecasting accuracy, the model integrates temporally lagged volatility information and information from adjacent nodes, which may instantaneously spill across the entire network. The model is also suitable for high-dimensional cases where multivariate ARCH models are typically no longer applicable. We adopt the theoretical foundations from spatiotemporal statistics and transfer the dynamic ARCH model for processes to networks. This new approach is compared with independent univariate log-ARCH models. We could quantify the improvements due to the instantaneous network ARCH effects, which are studied for the first time in this paper. The edges are determined based on various distance and correlation measures between the time series. The performances of the alternative networks' definitions are compared in terms of out-of-sample accuracy. Furthermore, we consider ensemble forecasts based on different network definitions.

Selecting an appropriate statistical model to forecast exchange rates is still today a relevant issue for policymakers and central bankers. The so-called Meese and Rogoff puzzle assesses that exchange rate fluctuations are unpredictable. In the literature, a lot of studies tried to solve the puzzle finding both alternative predictors (e.g., interest rates, price levels) and statistical models based on temporal aggregation. In this paper, we propose an approach based on mixed frequency models to overcome the lack of information caused by temporal aggregation. We show the effectiveness of our approach with an application to CAD/USD exchange rate predictions.

Well-being is a multidimensional concept that cannot be described using a single indicator. By the synthesis of different dimensions it is possible to obtain composite indicators (CIs). Principal Components Analysis (PCA) is one of the most popular multivariate statistical techniques used building CIs. However, the fact that PCA does not take into account the spatial dimension of the phenomenon makes it unsuitable for studying the well-being of urban areas. In this paper, we propose to use Spatial Principal Component Analysis (SPCA) for measuring well-being. The SPCA technique provides principal component scores that summarize both the spatial variability and the spatial autocorrelation structure among the statistical units. In this paper, the SPCA is used to construct well-being CIs for the Italian provinces.

The SARS-Cov-2 has spread differently over space and time worldwide. By monitoring the contagion’s time evolution, the November 3 2020 the Italian government introduced differentiated regime of restrictions among its regions. This experiment demonstrated that public health policies can be effectively designed by means of clustering. This paper proposes a fuzzy clustering model where spatial and temporal dimensions of the disease spread are optimally weighted. The resulting model is applied with the aim of identifying groups of Italian regions with similar contagion spread. We found that two groups of regions sharing similar patterns of COVID-19 spread over both space and time exist. Appropriate public health policies can be designed on the basis of this evidence.