Forecasting Stock Returns

Do Commodity Prices Help?

Angela J. Black, Olga Klinkowska, David G. McMillan*, Fiona J. McMillan

*Corresponding author for this work

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This paper examines the relationship between stock prices and commodity prices and whether this can be used to forecast stock returns. As both prices are linked to expected future economic performance they should exhibit a long-run relationship. Moreover, changes in sentiment towards commodity investing may affect the nature of the response to disequilibrium. Results support cointegration between stock and commodity prices, while Bai-Perron tests identify breaks in the forecast regression. Forecasts are computed using a standard fixed (static) in-sample/out-of-sample approach and by both recursive and rolling regressions, which incorporate the effects of changing forecast parameter values. A range of model specifications and forecast metrics are used. The historical mean model outperforms the forecast models in both the static and recursive approaches. However, in the rolling forecasts, those models that incorporate information from the long-run stock price/commodity price relationship outperform both the historical mean and other forecast models. Of note, the historical mean still performs relatively well compared to standard forecast models that include the dividend yield and short-term interest rates but not the stock/commodity price ratio. Copyright (c) 2014 John Wiley & Sons, Ltd.

Original languageEnglish
Pages (from-to)627-639
Number of pages13
JournalJournal of forecasting
Volume33
Issue number8
Early online date20 Oct 2014
DOIs
Publication statusPublished - Dec 2014

Keywords

  • stock prices
  • commodity prices
  • forecasting
  • rolling
  • expected returns
  • dividend yields
  • equity premium
  • cointegration
  • volatility
  • predictability
  • accuracy
  • vectors
  • models
  • breaks

Cite this

Black, A. J., Klinkowska, O., McMillan, D. G., & McMillan, F. J. (2014). Forecasting Stock Returns: Do Commodity Prices Help? Journal of forecasting, 33(8), 627-639. https://doi.org/10.1002/for.2314

Forecasting Stock Returns : Do Commodity Prices Help? / Black, Angela J.; Klinkowska, Olga; McMillan, David G.; McMillan, Fiona J.

In: Journal of forecasting, Vol. 33, No. 8, 12.2014, p. 627-639.

Research output: Contribution to journalArticle

Black, AJ, Klinkowska, O, McMillan, DG & McMillan, FJ 2014, 'Forecasting Stock Returns: Do Commodity Prices Help?', Journal of forecasting, vol. 33, no. 8, pp. 627-639. https://doi.org/10.1002/for.2314
Black, Angela J. ; Klinkowska, Olga ; McMillan, David G. ; McMillan, Fiona J. / Forecasting Stock Returns : Do Commodity Prices Help?. In: Journal of forecasting. 2014 ; Vol. 33, No. 8. pp. 627-639.
@article{06b88f71dff04c0889d94c1857f7b093,
title = "Forecasting Stock Returns: Do Commodity Prices Help?",
abstract = "This paper examines the relationship between stock prices and commodity prices and whether this can be used to forecast stock returns. As both prices are linked to expected future economic performance they should exhibit a long-run relationship. Moreover, changes in sentiment towards commodity investing may affect the nature of the response to disequilibrium. Results support cointegration between stock and commodity prices, while Bai-Perron tests identify breaks in the forecast regression. Forecasts are computed using a standard fixed (static) in-sample/out-of-sample approach and by both recursive and rolling regressions, which incorporate the effects of changing forecast parameter values. A range of model specifications and forecast metrics are used. The historical mean model outperforms the forecast models in both the static and recursive approaches. However, in the rolling forecasts, those models that incorporate information from the long-run stock price/commodity price relationship outperform both the historical mean and other forecast models. Of note, the historical mean still performs relatively well compared to standard forecast models that include the dividend yield and short-term interest rates but not the stock/commodity price ratio. Copyright (c) 2014 John Wiley & Sons, Ltd.",
keywords = "stock prices, commodity prices, forecasting, rolling, expected returns, dividend yields, equity premium, cointegration, volatility , predictability, accuracy, vectors, models, breaks",
author = "Black, {Angela J.} and Olga Klinkowska and McMillan, {David G.} and McMillan, {Fiona J.}",
year = "2014",
month = "12",
doi = "10.1002/for.2314",
language = "English",
volume = "33",
pages = "627--639",
journal = "Journal of forecasting",
issn = "0277-6693",
publisher = "John Wiley and Sons Ltd",
number = "8",

}

TY - JOUR

T1 - Forecasting Stock Returns

T2 - Do Commodity Prices Help?

AU - Black, Angela J.

AU - Klinkowska, Olga

AU - McMillan, David G.

AU - McMillan, Fiona J.

PY - 2014/12

Y1 - 2014/12

N2 - This paper examines the relationship between stock prices and commodity prices and whether this can be used to forecast stock returns. As both prices are linked to expected future economic performance they should exhibit a long-run relationship. Moreover, changes in sentiment towards commodity investing may affect the nature of the response to disequilibrium. Results support cointegration between stock and commodity prices, while Bai-Perron tests identify breaks in the forecast regression. Forecasts are computed using a standard fixed (static) in-sample/out-of-sample approach and by both recursive and rolling regressions, which incorporate the effects of changing forecast parameter values. A range of model specifications and forecast metrics are used. The historical mean model outperforms the forecast models in both the static and recursive approaches. However, in the rolling forecasts, those models that incorporate information from the long-run stock price/commodity price relationship outperform both the historical mean and other forecast models. Of note, the historical mean still performs relatively well compared to standard forecast models that include the dividend yield and short-term interest rates but not the stock/commodity price ratio. Copyright (c) 2014 John Wiley & Sons, Ltd.

AB - This paper examines the relationship between stock prices and commodity prices and whether this can be used to forecast stock returns. As both prices are linked to expected future economic performance they should exhibit a long-run relationship. Moreover, changes in sentiment towards commodity investing may affect the nature of the response to disequilibrium. Results support cointegration between stock and commodity prices, while Bai-Perron tests identify breaks in the forecast regression. Forecasts are computed using a standard fixed (static) in-sample/out-of-sample approach and by both recursive and rolling regressions, which incorporate the effects of changing forecast parameter values. A range of model specifications and forecast metrics are used. The historical mean model outperforms the forecast models in both the static and recursive approaches. However, in the rolling forecasts, those models that incorporate information from the long-run stock price/commodity price relationship outperform both the historical mean and other forecast models. Of note, the historical mean still performs relatively well compared to standard forecast models that include the dividend yield and short-term interest rates but not the stock/commodity price ratio. Copyright (c) 2014 John Wiley & Sons, Ltd.

KW - stock prices

KW - commodity prices

KW - forecasting

KW - rolling

KW - expected returns

KW - dividend yields

KW - equity premium

KW - cointegration

KW - volatility

KW - predictability

KW - accuracy

KW - vectors

KW - models

KW - breaks

U2 - 10.1002/for.2314

DO - 10.1002/for.2314

M3 - Article

VL - 33

SP - 627

EP - 639

JO - Journal of forecasting

JF - Journal of forecasting

SN - 0277-6693

IS - 8

ER -