nach oben

Empirical Economics

Erschienen in:

29.08.2017

Can oil prices help predict US stock market returns? Evidence using a dynamic model averaging (DMA) approach

verfasst von: Hanan Naser, Fatema Alaali

Erschienen in: Empirical Economics | Ausgabe 4/2018

Einloggen

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

search-config

KI-gestützte Suche

Aus

Abstract

Crude oil price behaviour has fluctuated wildly since 1973 which has a major impact on key macroeconomic variables. Although the relationship between stock market returns and oil price changes has been scrutinized excessively in the literature, the possibility of predicting future stock market returns using oil prices has attracted less attention. This paper investigates the ability of oil prices to predict S&P 500 price index returns with the use of other macroeconomic and financial variables. Including all the potential variables in a forecasting model may result in an over-fitted model. So instead, dynamic model averaging (DMA) and dynamic model selection (DMS) are applied to utilize their ability of allowing the best forecasting model to change over time while parameters are also allowed to change. The empirical evidence shows that applying the DMA/DMS approach leads to significant improvements in forecasting performance in comparison to other forecasting methodologies and the performance of these models are better when oil prices are included within predictors.

Vorheriger Artikel Quantile forecast combination using stochastic dominance

Nächster Artikel Consumer valuation of energy-saving features of residential air conditioners with hedonic and choice models

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!

Jetzt informieren

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!

Jetzt informieren

The pioneering work in the field of stock market research which is established by Chen et al. (1986) has investigated the effects of movements in macroeconomic variables on future dividends and discount rate, which consequently disturbs stock prices in the US. However, they argue that there is a long term relationship between macroeconomic variables and stock market.

Naser (2016) has examined the performance of DMA model in forecasting the prices of oil using a large data set. It is found that the performance of forecasting has significantly improved using the DMA which accounts for both time and model uncertainty.

Explanatory variables are all transformed to be stationary. For more details, see Sect. (3).

For more information, see Koop and Korobilis (2012).

For a complete description of Bayesian estimation of state-space model see Koop (2003), Kim and Nelson (1999).

As \(\lambda \) decreases, a greater and greater degree of coefficients change is allowed. As \(\lambda \rightarrow 0\), only most recent observations is used for forecasting. It is worth noting that McCormick et al. (2012) has improved on these methods by proposing an adaptive updating approach to specifying \(\lambda \).

For instance, if monthly data are used with \(\alpha =0.99\) then the forecasting model used 3 years ago receives around 70% as much weight as the forecasting model used last period. If \(\alpha =0.95\) then forecast performance 3 years ago receives only 16% weight.

Raftery et al. (2010) explain in details the use of this approximation

Note that, Grassi and de Magistris (2015) suggest that one could choose values for \(\lambda \) and \(\alpha \) on the basis of the forecast performance, however; this would not only bias the findings in favor of DMA, it is also not a valid procedure for the out-of-sample forecasting (Koop and Korobilis 2012). Hence, following Koop and Korobilis (2012), the values for the forgetting factors are simply selected to vary from 0.93 to 1.0.

Since Rapach et al. (2005) have used a univariate AR process to evaluate the performance of stock returns predictability without any information from other variables, this paper employs three classical models (i.e. with no TVP) including the random walk, single autoregressive, and multivariate simple regression model, to evaluate the forecast performance of the DMA and DMS models as shown in Sect. 4.

http://www.econ.yale.edu/~shiller/data.htm.

ADF and PPerron are the Augmented Dickey Fuller and Phillips–Perron tests with the null hypotheses of unit root and KPSS test is based on a null hypothesis of stationary time series.

Mollick and Assefa (2013) identify the crisis of 2008–2009 as a significant period of economic contraction and subsequent ‘recovery’, then stability of the stock-oil relationship has been checked by using GARCH and MGARCH-DCC models. Prior to the financial crisis, Mollick and Assefa (2013) find that stock returns are slightly (negatively) affected by oil prices. For the sub-sample of mid-2009 onwards, however, it is found that stock returns are positively affected by oil prices. In addition. it is worth to note that in periods of significant economic turmoil the oil market is not a safe haven for offering protection against stock market losses (Filis et al. 2011).

www.businessinsider.com/looks-like-1984-all-over-again-for-oil-2015-11.

For more information on selecting the values of forgetting factors, see Koop and Korobilis (2012).

Results are available upon request.

Basically, the dynamic model approach considers even the lags of the dependent and independent variables in model averaging and model selection. Accordingly, with two lags of the dependent variable, the total number of potential predictors come up to 13 potential predictors which increased the total number of possible models to 8192.

Arouri ME, Hedi AL, Nguyen DK (2011) Return and volatility transmission between world oil prices and stock markets of the gcc countries. Econ Model 28(4):1815–1825CrossRef

Avramov D (2002) Stock return predictability and model uncertainty. J Financ Econ 64(3):423–458CrossRef

Basher SA, Haug AA, Sadorsky P (2012) Oil prices, exchange rates and emerging stock markets. Energy Econ 34(1):227–240CrossRef

Campbell JY, Thompson SB (2008) Predicting excess stock returns out of sample: can anything beat the historical average? Rev Financ Stud 21(4):1509–1531CrossRef

Chang K-L, Shih-Ti Y (2013) Does crude oil price play an important role in explaining stock return behavior? Energy Econ 39:159–168CrossRef

Chen N-F, Roll R, Ross SA et al (1986) Economic forces and the stock market. J Bus 59(3):383CrossRef

Chen S-S (2009) Predicting the bear stock market: macroeconomic variables as leading indicators. J Bank Finance 33(2):211–223CrossRef

Chen S-S (2010) Do higher oil prices push the stock market into bear territory? Energy Econ 32(2):490–495CrossRef

Cogley T, Sargent TJ (2005) Drifts and volatilities: monetary policies and outcomes in the post WWII US. Rev Econ Dyn 8(2):262–302CrossRef

Cremers KJM (2002) Stock return predictability: a Bayesian model selection perspective. Rev Financ Stud 15(4):1223–1249CrossRef

Cunado J, de Gracia FP (2014) Oil price shocks and stock market returns: evidence for some European countries. Energy Econ 42:365–377CrossRef

Dickey DA, Fuller WA (1979) Distribution of the estimators for autoregressive time series with a unit root. J Am Stat Assoc 74(366a):427–431CrossRef

Diebold FX, Rudebusch GD (1991) Forecasting output with the composite leading index: a real-time analysis. J Am Stat Assoc 86(415):603–610CrossRef

Driesprong G, Jacobsen B, Maat B (2008) Striking oil: another puzzle? J Financ Econ 89(2):307–327CrossRef

Filis G, Degiannakis S, Floros C (2011) Dynamic correlation between stock market and oil prices: the case of oil-importing and oil-exporting countries. Int Rev Financ Anal 20(3):152–164CrossRef

Grassi S, de Magistris PS (2015) It’s all about volatility of volatility: evidence from a two-factor stochastic volatility model. J Empir Finance 30:62–78CrossRef

Groen JJJ, Paap R, Ravazzolo F (2013) Real-time inflation forecasting in a changing world. J Bus Econ Stat 31(1):29–44CrossRef

Hamilton JD (1989) A new approach to the economic analysis of nonstationary time series and the business cycle. Econ J Econ Soc 57(2):357–384

Hamilton JD (2011) Nonlinearities and the macroeconomic effects of oil prices. Macroecon Dyn 15(S3):364–378CrossRef

Henkel SJ, Spencer Martin J, Nardari F (2011) Time-varying short-horizon predictability. J Financ Econ 99(3):560–580CrossRef

Huang R, Masulis R, Stoll H (1996) Energy shocks and financial markets. J Futures Mark 16(1):1–27CrossRef

IEA (2014) Key world energy statistics. International Energy Agency, Paris

Inoue A, Kilian L (2005) In-sample or out-of-sample tests of predictability: which one should we use? Econ Rev 23(4):371–402CrossRef

Jones CM, Kaul G (1996) Oil and the stock markets. J Finance 51(2):463–491CrossRef

Justiniano A, Primiceri GE (2008) The time-varying volatility of macroeconomic fluctuations. Am Econ Rev 98(3):604–641CrossRef

Kilian L, Park C (2009) The impact of oil price shocks on the US stock market. Int Econ Rev 50(4):1267–1287CrossRef

Kim CJ, Nelson CR (1999) State-space models with regime switching: classical and Gibbs-sampling approaches with applications. MIT Press Books 1, Cambridge

Koop G, Korobilis D (2011) UK macroeconomic forecasting with many predictors: which models forecast best and when do they do so? Econ Model 28(5):2307–2318CrossRef

Koop G, Korobilis D (2012) Forecasting inflation using dynamic model averaging. Int Econ Rev 53(3):867–886CrossRef

Koop GM (2003) Bayesian econometrics. Wiley, New York

Kwiatkowski D, Phillips PCB, Schmidt P, Shin Y (1992) Testing the null hypothesis of stationarity against the alternative of a unit root: how sure are we that economic time series have a unit root? J Econ 54(1):159–178CrossRef

Liu L, Ma F, Wang Y (2015) Forecasting excess stock returns with crude oil market data. Energy Econ 48:316–324CrossRef

Ludvigson SC, Ng S (2007) The empirical risk-return relation: a factor analysis approach. J Financ Econ 83(1):171–222CrossRef

McCormick TH, Raftery AE, Madigan D, Burd RS (2012) Dynamic logistic regression and dynamic model averaging for binary classification. Biometrics 68(1):23–30CrossRef

Miller JI, Ratti RA (2009) Crude oil and stock markets: stability, instability, and bubbles. Energy Econ 31(4):559–568CrossRef

Mollick AV, Assefa TA (2013) US stock returns and oil prices: the tale from daily data and the 2008–2009 financial crisis. Energy Econ 36:1–18CrossRef

Narayan PK, Gupta R (2015) Has oil price predicted stock returns for over a century? Energy Econ 48:18–23CrossRef

Naser H (2016) Estimating and forecasting the real prices of crude oil: a data rich model using a dynamic model averaging (DMA) approach. Energy Econ 56:75–87CrossRef

Park J, Ratti RA (2008) Oil price shocks and stock markets in the US and 13 European countries. Energy Econ 30(5):2587–2608CrossRef

Pesaran MH, Timmermann A (1995) Predictability of stock returns: robustness and economic significance. J Finance 50(4):1201–1228CrossRef

Pesaran MH, Timmermann A (2000) A recursive modelling approach to predicting UK stock returns. Econ J 110(460):159–191CrossRef

Pesaran MH, Timmermann A (2002) Market timing and return prediction under model instability. J Empir Finance 9(5):495–510CrossRef

Phillips PCB, Perron P (1988) Testing for a unit root in time series regression. Biometrika 75(2):335–346CrossRef

Raftery AE, Kárnỳ M, Ettler P (2010) Online prediction under model uncertainty via dynamic model averaging: application to a cold rolling mill. Technometrics 52(1):52–66CrossRef

Rapach DE, Zhou G (2013) Forecasting stock returns. Handbook Econ Forecast 2(Part A):328–383CrossRef

Rapach DE, Strauss JK, Zhou G (2010) Out-of-sample equity premium prediction: combination forecasts and links to the real economy. Rev Financ Stud 23(2):821–862CrossRef

Rapach DE, Wohar ME, Rangvid J (2005) Macro variables and international stock return predictability. Int J Forecast 21(1):137–166CrossRef

Risse Marian, Kern Martin (2016) Forecasting house-price growth in the euro area with dynamic model averaging. Available at SSRN 2613394

Sadorsky P (1999) Oil price shocks and stock market activity. Energy Econ 21(5):449–469CrossRef

Sarno L, Valente G (2009) Exchange rates and fundamentals: footloose or evolving relationship? J Eur Econ Assoc 7(4):786–830CrossRef

Stock JH, Watson MW (2007) Introduction to econometrics. Addison-Wesley, Reading

Welch I, Goyal A (2008) A comprehensive look at the empirical performance of equity premium prediction. Rev Financ Stud 21(4):1455–1508CrossRef

White H (2000) A reality check for data snooping. Econometrica 68(5):1097–1126CrossRef

Titel: Can oil prices help predict US stock market returns? Evidence using a dynamic model averaging (DMA) approach
verfasst von: Hanan Naser
Fatema Alaali
Publikationsdatum: 29.08.2017
Verlag: Springer Berlin Heidelberg
Erschienen in: Empirical Economics / Ausgabe 4/2018
Print ISSN: 0377-7332
Elektronische ISSN: 1435-8921
DOI: https://doi.org/10.1007/s00181-017-1323-5

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

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

Springer Professional "Wirtschaft"

Springer Professional "Wirtschaft+Technik"

Weitere Artikel der Ausgabe 4/2018

A trend filtering method closely related to trend filtering

What is the right balance between US monetary and fiscal policy? Explorations using simulated wavelet-based optimal tracking control

The end of Brazilian big inflation: lessons to monetary policy from a standard New Keynesian model

Do parole abolition and Truth-in-Sentencing deter violent crimes in Virginia?

Central bank interventions in a dollarized economy: managed floating versus inflation targeting

The impact of financial development, economic growth, income inequality on poverty: evidence from India