Finance – Econometrics : “The US stock market reaction to oil price changes” (Graduate level)
The homework is to write a technical report / project / short essay (12 to 15 pages) in order to reproduce a research paper by implementing the same models
(regressions) (using matlab) and discuss it. The paper is “The stock market reaction to oil price changes” written by S.Gogineni (file enclosed).
The paper deals with the impact of daily oil price changes on the stock returns : index and industries individually, on a daily basis, from 1983 to 2006. It would be
better to replicate the experiments using a larger scale of data, for instance we could do the same thing for 1983-2015.
It’s mandatory that I deliver the written report (including tables etc in annex), the data used, the matlab code and / or excel sheets. (Self-containedness and correct
program execution are required)
Structure must be : Introduction – Problem statment – Solution methodology – Implementation detail – Results and comments – Annexes
To summarize, the objectif is to deeply understand the paper (the only source), to reproduce it, preferably including more recent data. I would say that this initial
paper aims at 3 things :
1) Investigation of the impact of oil price changes on the US market using daily data from 1983 to 2006
2) Examine the impact of oil prince changes on the returns of individual industries using a cost-side and demand-side dependance on oil from 1998 to 2006 (61 in this
paper, data from the Input-Output data from bureau of economic analysis to estimate industries cost-side and demand-side dependance measures)
3) Differentiate between the impact of daily oil price changes likely caused by supply shifts and those caused by changes in expectations about future economic
activity
Data : :
1) The author used daily weighted returns of NYSE / NASDAQ / AMEX index obtained from CRSP as a measure of stock market returns and daily cash price data of light
crude oil.
I don’t have access to these data, so you can use the source you want, but I will need the file you will have used. I don’t really know what’s the more convenient, but
it’s not mandatory that you use exactly the sames indexes. It would be preferable, but I mean that the aim of the work is to replicate the models and objectives of the
article, not necessarly from the same data etc
2) He used the benchmark input-output (IO) accounts published by the Bureau of Economic Analysis to calculate industries dependence on oil. I’m not really sure about
the file but I did find one of the two files about Input-Output balance the author mentionned. They are available from 1997 to 2015 for 71 industries
This is to implement the cost – side dependence = dollar value of oil used as an inpud / dollar value of industry’s output
I’ve uploaded a file but i’m not sure, so feel free to use the one that is the best to replicate the experiment, here is the link
https://www.bea.gov/industry/io_annual.htm
3) Data from 1) 2) for computing
Here are the hypothesis that the author tested using 10 simple regressions (cf tests / empirical results)
Relation between oil price changes and market returns
Hypothesis I: The stock market reacts negatively to oil price changes.
Hypothesis II: While large oil price changes have a large negative impact on market returns, the impact of small oil price changes is positive.
Market efficiency and oil price changes
Hypothesis III: The stock market under- reacts to daily oil price changes
Hypothesis IV: The stock market‟s reaction to oil price increases is larger than its reaction to oil price decreases.
Sensitivity of industry returns to oil price changes
Hypothesis V: There is a positive relationship between an industry‟s cost-side dependence on oil and its sensitivity to oil price changes.
Hypothesis VI: There is a positive relationship between an industry‟s demand-side dependence on oil and its sensitivity to oil price changes.
