Andersen (1996) writes that "price movements are caused primarely by the
arrival of new information and the process that incoprates this
information into market prices". This underlying information process affects stock market volatility and trade volumes. If Google Trends data represents the general flow of information then we should see a correlation between Google Trends data, volatility and volume.
The data set consists of daily Google Trends observations for the querry "FTSE 100" and daily returns, volatility and volume for FTSE 100. The correlation matrix shows that there is a high correlation between volatility and Google Trends data for the FTSE 100 data set.The correlation between the Google Trends data and volatility is surprisingly low, as is the correlation between volume and volatility.
Close | Trends | Return | Volatility | Volume | |||
Close | 1.00 | -0.28 | 0.04 | -0.24 | -0.10 | ||
Trends | 1.00 | -0.06 | 0.48 | -0.01 | |||
Return | 1.00 | 0.03 | -0.04 | ||||
Volatility | 1.00 | 0.16 | |||||
Volume | 1.00 | ||||||
Correlation matrix, FTSE 100 |
A univariate OLS regression where volatility is the dependent variable and Google Trends is the independent variable gives a significant slope on a 0.1% level and an R^2 of 23,51%.
Estimate | Std. Error | T value | Pr(>|t|) | ||
(Intercept) | 0.00 | 0.00 | -7.59 | 0.00 | *** |
Trends | 0.00 | 0.00 | 27.28 | 2e-16 | *** |
No comments:
Post a Comment