"Volatility estimator" is the right term to be googling. There isn't a simple way to even define the term volatility, although usually we use it as being equivalent to the standard deviation for a log-normal distribution. What *you* mean by the term "volatility" is really up to you.
Thats not BS thats R 8^) To be more terse: > # load a nice quant library... > require(quantmod) > # get the daily data from yahoo for a year back... > # do the close-to-close volatility calculation... > # display the end of the time series of volatility... > tail(volatility(getSymbols('aapl', auto.assign=FALSE), calc="close")) [,1] 2011-05-16 0.1466364 2011-05-17 0.1636225 2011-05-18 0.1759760 2011-05-19 0.1771079 2011-05-20 0.1881051 2011-05-23 0.1859659 > Hmmm... Four comments and two lines of code... And NO BS ;^) Cordially, -Digital Dude-
I have ended up going this route, more or less. I agree that things don't need to be overly complicated, just complicated enough to matter.