The impact of spatial elements on the forecasting of Spanish labour series

Angulo, Ana; Trívez, F. Javier

doi:10.1007/s10109-010-0118-4

Cited by 11 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schanne et al (2010) reach a similar conclusion, comparing a spatial global VAR (GVAR) model with time series methods. Angulo and Trívez (2010) find a substantial equivalence between a fixed effects panel spatial lag model and a series of non-spatial ARIMA models. On the other hand, Ohtsuka and Kakamu (2013) find that a VAR model outperforms a spatial autoregressive ARMA (SAR-ARMA) model.…”

Section: Methodology: Spatial Vector-autoregressive Models and Spatiamentioning

confidence: 87%

“…Within this framework, the discussion on the advantages and disadvantages of ex ante and ex post predictions seems unnecessary, since contemporaneous spatial lags are obtained in the first stage, as described in Section 2. Angulo and Trívez (2010) avoid this debate as well when employing a dynamic panel data model in forecasting employment levels in Spanish provinces.…”

Section: Evaluation Of Forecastsmentioning

confidence: 99%

See 1 more Smart Citation

Spatial Panel Data Forecasting over Different Horizons, Cross-Sectional and Temporal Dimensions

Mayor

Patuelli

2013

SSRN Journal

View full text Add to dashboard Cite

Empirical assessments of the forecasting power of spatial panel data econometric models are still scarcely available. Moreover, several methodological contributions rely on simulated data to showcase the potential of proposed methods. While simulations may be useful to evaluate the properties of a single estimator, the empirical set-ups of simulation studies are often based on strong assumptions regarding the shape and regularity of the statistical distribution of the variables involved. It is then valuable to have, next to simulation studies, empirical assessments of competing econometric models based on real data. In this paper, we evaluate competing spatial (dynamic) panel methods, selecting a number of data sets characterized by a range of different crosssectional and temporal dimensions, as well as different levels of spatial autocorrelation. We carry out our empirical exercise on regional unemployment data for France, Spain and Switzerland. Additionally, we test different forecasting horizons, in order to investigate the speed of deterioration of forecasting quality. We compare two classes of methods: spatial vector autoregressive (SVAR) models and dynamic panel models making use of eigenvector spatial filtering (SF). We find that, as it could be expected, the unbalance between the temporal and cross-sectional dimension (T >> n) does play in favour of the SVAR model. On the other hand, the advantage of the SVAR model over the SF model appears to diminish as the forecasting horizon widens, eventually leading the SF model to being preferred for more distant forecasts.

show abstract

Section: Methodology: Spatial Vector-autoregressive Models and Spatiamentioning

confidence: 87%

Section: Evaluation Of Forecastsmentioning

confidence: 99%

Spatial Panel Data Forecasting over Different Horizons, Cross-Sectional and Temporal Dimensions

Mayor

Patuelli

2013

SSRN Journal

View full text Add to dashboard Cite

show abstract

“…Within this framework, the discussion on the advantages and disadvantages of ex-ante and ex-post predictions seems unnecessary, since contemporaneous spatial lags are obtained in the first stage, as described above. Angulo and Trívez (2010) (Model 2) forecasts which show a greater error than the one of SVAR (Model 1) may be expected to be 50 per cent of the total number of forecasts obtained. Consequently, Model 1 will be considered superior to Model 2 if Model 2 has higher forecasting errors in more than 50 per cent of the cases.…”

Section: Resultsmentioning

confidence: 98%

Short-Run Regional Forecasts: Spatial Models Through Varying Cross-Sectional and Temporal Dimensions

Patuelli

Mayor

2012

SSRN Journal

View full text Add to dashboard Cite

In any economic analysis, regions or municipalities should not be regarded as isolated spatial units, but rather as highly interrelated small open economies. These spatial interrelations must be considered also when the aim is to forecast economic variables. For example, policy makers need accurate forecasts of the unemployment evolution in order to design short-or long-run local welfare policies. These predictions should then consider the spatial interrelations and dynamics of regional unemployment. In addition, a number of papers have demonstrated the improvement in the reliability of long-run forecasts when spatial dependence is accounted for. We estimate a heterogeneouscoefficients dynamic panel model employing a spatial filter in order to account for spatial heterogeneity and/or spatial autocorrelation in both the levels and the dynamics of unemployment, as well as a spatial vector-autoregressive (SVAR) model. We compare the short-run forecasting performance of these methods, and in particular, we carry out a sensitivity analysis in order to investigate if different number and size of the administrative regions influence their relative forecasting performance. We compute short-run unemployment forecasts in two countries with different administrative territorial divisions and data frequency: Switzerland (26 regions, monthly data for 34 years) and Spain (47 regions, quarterly data for 32 years) 2

show abstract

“…Giacomini and Granger (2004) arguably offered the seminal paper in this literature. In recent years, more and more papers have moved toward forecasting with dynamic, spatial econometric models (Kholodilin et al, 2008;Angulo and Javier Trivez, 2010;Schanne et al, 2010;Kholodilin and Mense, 2012;Ohtsuka and KaKamu, 2013). A few papers have used this methodology to examine the sub-national forecasts of carbon dioxide emissions (Auffhammer and Steinhauser, 2007;Auffhammer and Carson, 2008;Auffhammer and Steinhauser, 2012).…”

Section: Development Of Spatial Econometric Modelsmentioning

confidence: 99%

Three Essays on Investigating Province-Level Carbon Dioxide Emissions in China

Zhao¹

View full text Add to dashboard Cite

The three essays in this dissertation study the influential factors of energy-related carbon dioxide emission intensity, whether the province-level carbon dioxide emission intensity is convergence, and how spatial panel data models forecast compare with those from non-spatial panel data models for province-level carbon dioxide emissions in China. The first essay entitled "Spatial Analysis of China Province-Level CO2 Emission Intensity" offers a unique contribution to the literature by investigating the influential factors of energyrelated carbon dioxide emission intensity among a panel of 30 provinces in China covering the period 1990-2010. This study uses novel spatial panel data models to analyze those factors that influence energy-related emission intensity, which are characterized by spatial dependence. It is found that emission intensities are negatively related to per-capita, province-level GDP and population density. This relationship implies that promoting local economic development and population concentration may help to reduce CO2 emission intensity. In addition, emission intensities are positively affected by energy consumption structure and transportation structure. These empirical evidences indicate that Chinese government should encourage the development of less carbon-intensive energy resources and further fuel efficiency standards in its transportation sector. Finally, energy prices have no significant effect on emission intensities. This finding may suggest that the Chinese government should further deregulate energy prices to reduce artificial price distortions. The second essay entitled "Province-Level Convergence of China CO2 Emission Intensity" further explores the convergence of province-level CO2 emission intensity among a panel of 30 provinces in China over the period 1990-2010. This study use a novel, spatial dynamic panel data model to evaluate an empirically testable hypothesis of convergence among provinces. Based on the estimation results, I find evidence that CO2 emission intensities are converging across provinces in China. Moreover, the rate of convergence is higher with the dynamic panel data model (conditional convergence) than with a cross-sectional regression model (absolute convergence). This result suggests that the individual effects that are ignored in cross-sectional regressions potentially create omitted variable bias and the panel data framework arguably offers a more precise (efficiency) rate of convergence. Finally, it is found that province-level CO2 emission intensities are spatially correlated, and the rate of convergence, when controlling for spatial autocorrelation, is higher than with the non-spatial models. This result indicates that technological spillovers, embodied in both the unobserved individual effects and the spatial autocorrelation coefficient, have a direct effect on the rate of convergence of carbon intensity among provinces. The third essay entitled "Forecasting Province-Level CO2 Emissions in China" examines the performance of spatial panel data mo...

show abstract

The impact of spatial elements on the forecasting of Spanish labour series

Abstract: Dynamic spatial panel data models, ARIMA models, Forecast, Spanish provinces employment, C21, C22, C23, C53, R15,

Cited by 11 publications

References 33 publications

Spatial Panel Data Forecasting over Different Horizons, Cross-Sectional and Temporal Dimensions

Spatial Panel Data Forecasting over Different Horizons, Cross-Sectional and Temporal Dimensions

Short-Run Regional Forecasts: Spatial Models Through Varying Cross-Sectional and Temporal Dimensions

Three Essays on Investigating Province-Level Carbon Dioxide Emissions in China

Contact Info

Product

Resources

About