Predicting Stock Markets with Commodities - An Empirical Study on the Nordic Market
(2017) NEKN02 20171Department of Economics
- Abstract
- This study examines if commodity indices can be used to predict stock index returns on the Nordic financial markets. With a forecast period between 2000 and 2016, the study is conducted with an Ordinary Least Squares method to predict both in-sample and out-of- sample. The results indicate that the Baltic Dry Index and the London Metal Exchange Index are the best predictors of monthly stock returns for in-sample predictability. When testing for state-switching abilities of the commodity variables, we observe that predictability is only found in recessions and disappears in expansions. We also find evidence pointing in the direction of increasing commodity prices being better news in recessions than in expansions. Our estimates perform... (More)
- This study examines if commodity indices can be used to predict stock index returns on the Nordic financial markets. With a forecast period between 2000 and 2016, the study is conducted with an Ordinary Least Squares method to predict both in-sample and out-of- sample. The results indicate that the Baltic Dry Index and the London Metal Exchange Index are the best predictors of monthly stock returns for in-sample predictability. When testing for state-switching abilities of the commodity variables, we observe that predictability is only found in recessions and disappears in expansions. We also find evidence pointing in the direction of increasing commodity prices being better news in recessions than in expansions. Our estimates perform poorly out-of-sample, indicating that the information possessed by our predictions is of little use for an investor seeking profitable investment opportunities. The portfolios based on the significance of our estimators fail to outperform their respective benchmark index in 25 out of 28 cases. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/8910371
- author
- Söderlund Tovi, Sebastian LU and Kjellgren, John
- supervisor
-
- Hans Byström LU
- organization
- course
- NEKN02 20171
- year
- 2017
- type
- H1 - Master's Degree (One Year)
- subject
- keywords
- Commodities, stock returns, predictability, state-switching, trading strategy
- language
- English
- id
- 8910371
- date added to LUP
- 2017-06-13 15:18:17
- date last changed
- 2017-06-13 15:18:17
@misc{8910371, abstract = {{This study examines if commodity indices can be used to predict stock index returns on the Nordic financial markets. With a forecast period between 2000 and 2016, the study is conducted with an Ordinary Least Squares method to predict both in-sample and out-of- sample. The results indicate that the Baltic Dry Index and the London Metal Exchange Index are the best predictors of monthly stock returns for in-sample predictability. When testing for state-switching abilities of the commodity variables, we observe that predictability is only found in recessions and disappears in expansions. We also find evidence pointing in the direction of increasing commodity prices being better news in recessions than in expansions. Our estimates perform poorly out-of-sample, indicating that the information possessed by our predictions is of little use for an investor seeking profitable investment opportunities. The portfolios based on the significance of our estimators fail to outperform their respective benchmark index in 25 out of 28 cases.}}, author = {{Söderlund Tovi, Sebastian and Kjellgren, John}}, language = {{eng}}, note = {{Student Paper}}, title = {{Predicting Stock Markets with Commodities - An Empirical Study on the Nordic Market}}, year = {{2017}}, }