MIDAS Regressions: Further Results and New Directions

Ghysels, Éric; Sinko, Arthur; Valkanov, Rossen

doi:10.1080/07474930600972467

Cited by 786 publications

(561 citation statements)

References 84 publications

Supporting

Mentioning

514

Contrasting

Unclassified

Order By: Relevance

“…Ghysels, Santa-Clara, and Valkanov (2006a) and Ghysels, Sinko, and Valkanov (2006b) give detailed discussions of the advantages of using flexible functional forms for capturing volatility. Here we give a brief example that illustrates one benefit of using flexible functional forms for computing cross-sectional variances.…”

Section: An Example Of Flexible Weightsmentioning

confidence: 99%

“…Note that a potentially large set of weights is tightly parameterized via a small set of parameters. Ghysels, Santa-Clara, and Valkanov (2006a) and Ghysels, Sinko, and Valkanov (2006b) discuss how, by varying parameters, the discretized Beta distribution can capture many different weighting schemes associated with time series memory decay patterns observed in volatility dynamics and other persistent time series processes. They also observe that setting α = 1 yields downward sloping weighting schemes typically found in models of volatility predictions.…”

Section: Measuring Risk With Volatilitymentioning

confidence: 99%

See 1 more Smart Citation

The impact of risk and uncertainty on expected returns☆

Anderson

Ghysels

Juergens

2009

Journal of Financial Economics

Self Cite

365

194

View full text Add to dashboard Cite

We study asset pricing when agents face risk and uncertainty and empirically demonstrate that uncertainty has a substantial effect on asset prices. We measure risk with past volatility and uncertainty with the degree of disagreement of professional forecasters, attributing different weights to each forecaster. We run regressions representing the typical risk-return trade-off and augment these regressions with a measure of uncertainty. We find stronger empirical evidence for a uncertainty-return trade-off than for the traditional risk-return trade-off. We investigate the performance of a two-factor model with risk and uncertainty in the cross-section. * Evan Anderson: Northern Illinois University, Department of Economics, Zulauf 515, DeKalb, IL 60115, phone: (630) 450-0533, email: ewanderson@niu.edu. Eric Ghysels: Department of Finance, Kenan-Flagler Business School, and Department of Economics, University of North Carolina -Chapel Hill, Chapel Hill, NC 27599-3305, phone: (919) 966-5325, email: eghysels@unc.edu. Jennifer L. Juergens: Arizona State University, W.P. Carey School of Business, Department of Finance, Tempe, AZ 85287, phone: (480) 965-3131, email: Jennifer.Juergens@asu.edu. We would like to thank Lars Hansen, Peter Hansen, Chris Jones, Leonid Kogan, Jianjun Miao, Athanasios Orphanides, Simon Potter, Eric Renault, Robert Rich, Tom Sargent and Raman Uppal for very helpful comments. This paper was presented at Northern Illinois University, SAMSI Opening Workshop, 2006 EFA meetings, 2006 Winter Meetings of the Econometric Society, the SAMSI Conference on Model Uncertainty, 2006 NBER Summer Institute Asset Pricing Workshop, 2007 AFA meetings, UC Santa Cruz, University of Illinois at Urbana-Champaign, and University of Wisconsin-Madison. Early versions of the ideas in this paper were also presented at the Board of Governors, the FDIC, the Federal Reserve Bank of New York, Simon Fraser University and Stanford University. We thank seminar participants for helpful comments.Electronic copy of this paper is available at: http://ssrn.com/abstract=890621One of the most studied theoretical relationships in empirical finance is that the expected excess return of the market over a risk-free bond should vary positively and proportionally to the volatility of the market return. This risk-return trade-off is so fundamental that it could well be described as the "first fundamental law of finance." Merton (1973) derived this theoretical relationship in a continuous time model in which all agents have power preferences and hedging concerns are negligible, and it is sometimes referred to as Merton's ICAPM or simply the ICAPM.The empirical evidence for a risk-return trade-off is mixed. Many studies have run versions of the following regression:where r et+1 is the excess return of the market over a risk-free bond, γ is a risk aversion coefficient, and V t is (market) risk. 1 The goal has been to find a significantly positive γ coefficient that captures the trade-off between risk and return. Baillie and DeGennaro (199...

show abstract

Section: An Example Of Flexible Weightsmentioning

confidence: 99%

Section: Measuring Risk With Volatilitymentioning

confidence: 99%

The impact of risk and uncertainty on expected returns☆

Anderson

Ghysels

Juergens

2009

Journal of Financial Economics

Self Cite

365

194

View full text Add to dashboard Cite

show abstract

“…On the one hand, there are event studies, such as that by Karolyi et al (1996), which investigate how US macroeconomic announcements a¤ect the correlation between Japanese and US stocks using daily data from 1988 to 1992. Other researchers have used Mixed-data sampling methods (MIDAS), as in Ghysels et al (2006), Ghysels et al (2007). One example is Engle et al (2013) that analyses the relation between stock market volatility and macroeconomic activity since the 19th century, distinguishing short-run from secular movements.…”

Section: Introductionmentioning

confidence: 99%

In search of the determinants of European asset market comovements

Gomes

Taamouti

2016

International Review of Economics & Finance

View full text Add to dashboard Cite

Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-pro t purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. The information improves the portfolio performance compared to an equally weighted portfolio.JEL Classi…cation: C22, G12, G15, G17, E44.

show abstract

“…The MIDAS regression is introduced by Anderou and Ghysels (2004) and Ghysels et al (2006). It allows data from different frequencies to enter into the same model.…”

Section: Introductionmentioning

confidence: 99%

Macro-Finance Determinants of the Long-Run Stock-Bond Correlation: The DCC-MIDAS Specification

2014

View full text Add to dashboard Cite

Abstract:We investigate the long-run stock-bond correlation using a novel model that combines the dynamic conditional correlation model with the mixed-data sampling approach. The long-run correlation is affected by both macro-finance variables (historical and forecasts) and the lagged realized correlation itself. Macro-finance variables and the lagged realized correlation are simultaneously significant in forecasting the long-run stock-bond correlation. The behavior of the long-run stock-bond correlation is very different when estimated taking the macro-finance variables into account. Supporting the flight-to-quality phenomenon for the total stock-bond correlation, the long-run correlation tends to be small/negative when the economy is weak.

show abstract

MIDAS Regressions: Further Results and New Directions

Cited by 786 publications

References 84 publications

The impact of risk and uncertainty on expected returns☆

The impact of risk and uncertainty on expected returns☆

In search of the determinants of European asset market comovements

Macro-Finance Determinants of the Long-Run Stock-Bond Correlation: The DCC-MIDAS Specification

Contact Info

Product

Resources

About