Skip to main content

22.05.2024

Macroeconomic attention and commodity market volatility

verfasst von: Fameliti Stavroula, Skintzi Vasiliki

Erschienen in: Empirical Economics

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

In this paper, we empirically examine the relationship between the novel macroeconomic attention indices (MAI) and commodity market volatility. In-sample analysis indicates that MAI contribute significantly to the volatility fluctuations in commodity markets. In addition, we employ dimension reduction techniques, shrinkage methods, and combination models in an out-of-sample exercise to assess the predictive ability of MAI, alongside a variety of economic predictors including uncertainty measures, and global as well as US economic indicators. Our empirical results demonstrate the superior predictive ability of the elastic net and LASSO models incorporating MAI together with macroeconomic and uncertainty indicators. This empirical finding is reinforced through a series of robustness checks. However, dimension reduction methods exhibit superior performance in longer forecast horizons. Finally, MAI are more informative for commodity volatility forecasting during economic expansions and non-crisis periods. Our study offers new insights on commodity volatility forecasting.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Fußnoten
1
A significant number of studies (e.g., Wei et al. 2017; Liu et al. 2021; Díaz et al. 2021) has considered newspaper-based indicators in forecasting commodity prices and volatility and reports evidence of superior predictive ability.
 
2
For the LASSO regression, the \(a\) parameter is set to 1 in all cases.
 
3
Table 10 in the Appendix I presents the descriptive statistics of the data, as well as the data sources. We also employ the Augmented-Dickey Fuller (ADF) test to ensure the stationarity of each time series, while we take the first differences to address non-stationary series.
 
4
Each commodity in the S&P GSCI is weighted according to global production. More details on the weighting approach can be found at https://​www.​goldmansachs.​com/​what-we-do/​FICC-and-equities/​business-groups/​sts-folder/​gsci/​.
 
5
We have also conducted the same analysis using a rolling forecasting window and concluded to similar results. The results of the rolling window exercise are available upon request.
 
6
Beyond the R2OOS, we also evaluate the forecasting performance of our proposed models via four widely used statistical loss functions. The methodology and the results are presented in the AppendixII.
 
7
Table 2 presents the estimation results based on the AR(2) model is selected as the best fitting model using the BIC criterion. Additionally, we employed the Akaike Information Criterion (AIC) criterion to determine the appropriate number of lags concluding to quite similar results. These results are available upon request.
 
8
Specifically, we present only the R2OOS for the dimensionality reduction, shrinkage and combination models in Appendix III in order to save space. The results for the rest statistical measures and the individual models are available upon request.
 
9
To employ the WN model, we estimate Eq. (3) using the bias-adjusted feasible generalized least squares (FGLS) estimators. The resulting predictive model is: $${RV}_{t+1}=a+{{\sum }_{p=1}^{P}{a}_{p}R{V}_{t-p}+\beta }^{adj}{X}_{t}+\gamma \left({X}_{t+1}-{\varphi X}_{t}\right)+{e}_{t}$$, where $${\beta }^{adj}$$ is the bias-corrected predictability coefficient while the term $$\gamma \left({X}_{t+1}-{\varphi X}_{t}\right)$$ is included to account for any inherent persistence effect as well as endogeneity bias. We further control for heteroscedasticity by pre-weighting with the inverse of the standard deviation of the residual obtained from an AutiRegressive Conditional Heteroscedasticity (ARCH) process: $${\widehat{\sigma }}_{\tau ,t+1}^{2}={\omega }_{t}+\sum _{i=1}^{q}{\omega }_{i}{\widehat{e}}_{t-i}^{2}$$.
 
Literatur
Zurück zum Zitat Frankel JA (2008) The effect of monetary policy on real commodity prices. In: Campbell JY (ed) Asset prices and monetary policy. University of Chicago Press, Chicago Frankel JA (2008) The effect of monetary policy on real commodity prices. In: Campbell JY (ed) Asset prices and monetary policy. University of Chicago Press, Chicago
Zurück zum Zitat Wold H (1966) Estimation of principal components and related models by iterative least squares. In: Krishnajah PR (ed) Multivariate analysis. Academic Press, New York Wold H (1966) Estimation of principal components and related models by iterative least squares. In: Krishnajah PR (ed) Multivariate analysis. Academic Press, New York
Metadaten
Titel
Macroeconomic attention and commodity market volatility
verfasst von
Fameliti Stavroula
Skintzi Vasiliki
Publikationsdatum
22.05.2024
Verlag
Springer Berlin Heidelberg
Erschienen in
Empirical Economics
Print ISSN: 0377-7332
Elektronische ISSN: 1435-8921
DOI
https://doi.org/10.1007/s00181-024-02613-z

Premium Partner