You should phrase your research question in a way that matches up with the scope of inference your dataset allows for.
We examine the impact of FOMC cycle meetings upon equity market returns in the US. The Federal Reserve (FOMC) meetings have a substantial impact on equity market returns. One paper 2014 by Cieslak, Morse and Vissing-Jorgenson argues that the equity premium in the US has been earned entirely in the weeks 0, 2, 4, and 6 of the FOMC cycle.
We will seek to replicate the Cieslak, Morse and Vissing-Jorgenson result using available public data and extend the analysis to the recent period in Q1 2019.
What are the cases, and how many are there?
The observations are the roughly 200 FOMC cycle dates available since 1994. There are normally 8 FOMC meetings per year. Interest rate movement decisions are made on these dates.
Describe the method of data collection.
We will gather FOMC dates from the Federal Reserve website. We then gather historical SP500 Index returns (for the stock market) from FRED [https://fred.stlouisfed.org] where data is free to download.
FOMC decisions are interest rates are available from the Federal Reserve website and also FRED.
What type of study is this (observational/experiment)?
This is an observational study.
If you collected the data, state self-collected. If not, provide a citation/link.
The data will be self-collected from various sources.
What is the response variable? Is it quantitative or qualitative?
There are at least 2 possible quantitative response variables:
SP500 Index returns, MSCI Global Equity Index returns, US Treasury interest rates (short term T-Bill and 2, 5, 10 year rates)
You should have two independent variables, one quantitative and one qualitative.
There are at least 8 qualitative variables. Dummies for each week of the FOMC cycle.
A linear regression on non-Fed news including macro new releases and corporate earnings announcments is used to show that these other variables have no explanatory power for US stock daily excess returns.
Provide summary statistics for each the variables. Also include appropriate visualizations related to your research question (e.g. scatter plot, boxplots, etc). This step requires the use of R, hence a code chunk is provided below. Insert more code chunks as needed.
I have previously tested this pattern myself informally and found the stock returns to be consistent with the paper’s finding. It has economic implications in that financial trading strategies can and have been devised based on this paper.
Some key statistics to show would be a time series plot of average 5 day stock returns vs. days since the last FOMC meeting.
Other summary statistics of interest are the profitability of holding stocks on the weeks 0,2,4,6, only and evaluating strategy profits over time.
Reference to the paper is:
Anna Cieslak, Adair Morse, Annette Vissing-Jorgenson, “Stock Returns over the FOMC Cycle”, 2018 draft [http://faculty.haas.berkeley.edu/vissing/cieslak_morse_vissingjorgensen.pdf]