Spillover dynamics for systemic risk measurement using spatial financial time series models

Blasques, Francisco; Koopman, Siem Jan; Schaumburg, Julia

doi:10.1016/j.jeconom.2016.09.001

Cited by 108 publications

(115 citation statements)

References 51 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…The first one is that, from a theoretical perspective, ML estimation of GAS models is an on-going research topic. General results are reported by Harvey (2013), Blasques, Koopman, and Lucas (2014a) and Blasques, Koopman, and Lucas (2014b), while results for specific models have been derived by Andres (2014) and Blasques et al (2016b).…”

Section: Maximum Likelihood Estimationmentioning

confidence: 80%

“…It does not matter whether they are real-valued, integer-valued, (0, 1)-bounded or strictly positive, as long as there is a conditional density for which the score function and the Hessian are well-defined. The practical relevance of the GAS framework has been illustrated in the case of financial risk forecasting (see e.g., Harvey and Sucarrat (2014) for market risk, Oh and Patton (2016) for systematic risk, and Creal, Schwaab, Koopman, and Lucas (2014) for credit risk analysis), dependence modeling (see e.g., Harvey and Thiele (2016) and Janus, Koopman, and Lucas (2014)), and spatial econometrics (see e.g., Blasques, Koopman, Lucas, and Schaumburg (2016b) and Catania and Billé (2017)). For a more complete overview of the work on GAS models, we refer the reader to the GAS community page at http://www.gasmodel.com/.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generalized Autoregressive Score Models in R: The GAS Package

Ardia¹,

Boudt²,

Catania³

2019

J. Stat. Soft.

View full text Add to dashboard Cite

This paper presents the R package GAS for the analysis of time series under the generalized autoregressive score (GAS) framework of Creal, Koopman, and Lucas (2013) and Harvey (2013). The distinctive feature of the GAS approach is the use of the score function as the driver of time-variation in the parameters of non-linear models. The GAS package provides functions to simulate univariate and multivariate GAS processes, to estimate the GAS parameters and to make time series forecasts. We illustrate the use of the GAS package with a detailed case study on estimating the time-varying conditional densities of financial asset returns.

show abstract

Section: Maximum Likelihood Estimationmentioning

confidence: 80%

Section: Introductionmentioning

confidence: 99%

Generalized Autoregressive Score Models in R: The GAS Package

Ardia¹,

Boudt²,

Catania³

2019

J. Stat. Soft.

View full text Add to dashboard Cite

show abstract

“…The ML estimator (MLE) has been proved by Blasques et al (2016) to be consistent and asymptotically normal for the case of the spatial Durbin model, with only time-varying spatial effects. In the spatial literature, Bao and Ullah (2007) are no significant effects carried out by X t , so we simply set X t = 0.…”

Section: Finite Sample Properties Of the ML Estimatormentioning

confidence: 99%

“…The ideal situation would be defining an economic measure of distance without crashing into the endogeneity. For example, Blasques et al (2016) use a weighting matrix by exploiting countries cross-border debt data for their application in CDS. In studies on sectoral indices returns, however, the issue of finding appropriate economic information is more complicated.…”

Section: Distance In Financementioning

confidence: 99%

“…However, most of these emerging analyses are typically based on panel data with no time-varying spatial spillover effects. In line with Blasques et al (2016), we develop a nonlinear dynamic spatial model with time-varying autoregressive coefficients. The reason why we focus on a SARAR specification is also sustained by suspected unobserved shocks, e.g., consumers' perceptions, that can have indirect effects on the entire financial system in our empirical application.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Spatial Autoregressive Models with Autoregressive and Heteroskedastic Disturbances

Catania

Billé

2016

SSRN Journal

View full text Add to dashboard Cite

We propose a new class of models specifically tailored for spatio-temporal data analysis. To this end, we generalize the spatial autoregressive model with autoregressive and heteroskedastic disturbances, i.e., SARAR(1,1), by exploiting the recent advancements in Score Driven (SD) models typically used in timeseries econometrics. In particular, we allow for time-varying spatial autoregressive coefficients as well as time-varying regressor coefficients and cross-sectional standard deviations. We report an extensive Monte Carlo simulation study in order to investigate the finite sample properties of the Maximum Likelihood estimator for the new class of models as well as its flexibility in explaining a misspecified dynamic spatial dependence process. The new proposed class of models are found to be economically preferred by rational investors through an application to portfolio optimization.Modeling spatio-temporal data has recently received an increasing amount of attention, with applications that span from time geography to spatial panel data econometrics (see An et al., 2015).Specifically to the econometric field, researchers were focused on how to manage the raising availability of panel data by proposing a new class of dynamic spatial autoregressive models able to deal with: (i) serial dependence between the observations on each spatial unit over time, (ii) spatial dependence between the observations at each point in time, (iii) unobservable spatial and/or time-period-specific effects, (iv) endogeneity of one or more of the regressors other than dependent variables lagged in space and/or time (see Elhorst, 2012). According to the type of restriction that we impose, one may obtain several dynamic spatial sub-models. For instance, a time-space dynamic model can be obtained if we impose restrictions on the spatio-temporal evolution of the regressors, or a time-space recursive model if we ignore spatial autocorrelation but we account for time/space-lagged dependent variable and eventually for spatiallylagged regressors (see Elhorst, 2010;LeSage and Pace, 2009). As Anselin et al. (2008) stressed, however, the sub-general time-space dynamic model still may suffer from identification problems 1 , which led to the

show abstract

Research on financial data analysis based on data mining algorithm

2018

Concurrency and Computation

View full text Add to dashboard Cite

SummaryAt present, computer technology and Internet technology have been deeply integrated with the development of the Internet. This paper constructs a financial time series analysis and prediction model under the background of Internet e‐commerce development. As IT technology, data mining must be simple and fast. Therefore, starting from the model and based on the algorithm, this paper establishes a feasible serial data mining technology and theoretical system. Based on this, this paper deeply studies the data repair technology and interpolation technology such as EM algorithm for the actual more missing data, and the result is very satisfactory. Finally, this paper further studies the forward search algorithm, which is based on clustering to pretreat can complete the calculation process in a shorter time, reduce the possibility of errors, and improve efficiency.

show abstract

Spillover dynamics for systemic risk measurement using spatial financial time series models

Cited by 108 publications

References 51 publications

Generalized Autoregressive Score Models in R: The GAS Package

Generalized Autoregressive Score Models in R: The GAS Package

Dynamic Spatial Autoregressive Models with Autoregressive and Heteroskedastic Disturbances

Research on financial data analysis based on data mining algorithm

Contact Info

Product

Resources

About