Ralph Winters
  • Member for 10 years, 11 months
  • Last seen more than 1 year ago
Cluster analysis vs PCA for risk models?
7 votes

They are not mutually exclusive. PCA and clustering are similar but used for different purposes. You could use PCA to whittle down 10 risk factors to say 4 uncorrelated factors, and you could combine ...

View answer
Keeping a track record honest
6 votes

One thing I can think of: On your blog/newletter, offer to send daily email updates of your results to them. That way no one can say that you backdate results, or otherwise altered results. And I'm ...

View answer
When to shut down a trend following strategy?
6 votes

You can use a equity based model. Stop trading when your equity drops below your "X-day" equity moving average, and resume trading when your equity crosses above the "X day" equity moving average. You ...

View answer
better estimator of volatility for small samples
Accepted answer
5 votes

You could use something like the interquartile or semi-interquartile range, which is somewhat more insensitive to extremes. This is a better measure to use if your data is skewed, however if your data ...

View answer
Methods for pricing options
5 votes

I would also look into pricing models based upon models other than lognormal (Black-Scholes). Do some research on "fat tailed" or stable distributions. There can also be known by their specific ...

View answer
Separating the wheat from the chaff: What quant methods separate skillful managers from lucky ones?
4 votes

I was going to suggest that you use alpha, which is the measure of a managers excess return beyond their benchmark. But here is an alternative view which is quite interesting. http://money.usnews....

View answer
Time-series similarity measures
4 votes

If you use a Box-Jenkins model, look at this research which uses an ARIMA framework to define clusters, and then measures the similarity of the time series via a cepstral coefficient based upon the ...

View answer
Seeking Historical Non-Finance Datapoints for Backtesting
4 votes

Here is another link to some non-financial data sets from the University of California Machine Learning Repository: http://www.ics.uci.edu/~mlearn/MLRepository.html

View answer
How do you correct Max Draw-Down for auto-correlation?
3 votes

Have you considered a Monte Carlo simulation on your returns? Then you could look at the distribution of Maximum Drawdowns.

View answer
Using Black-Scholes equations to "buy" stocks
2 votes

Yes, this certainly is valid point of view, if you are thinking about purchase the stock outright rather than with options. In theory, if the Implied Volatility of calls was significantly higher the ...

View answer
How to compute momentum from equity time series?
2 votes

It sounds as if you would be interested in computing Relative Strength http://www.investopedia.com/terms/r/relativestrength.asp You could either measure it against a benchmark index such as the Dow ...

View answer
How to conduct Monte Carlo simulations to test validity of Black Scholes for a specific option?
0 votes

I think what you really need to do is test the results of the analytic/simulated solution against the actual AND future historical price. So you need to get historical data for the specific option. ...

View answer
How would one price a "credit event binary option"?
0 votes

The CBOE site states that the premium will approximately reflect the probability of bankruptcy. Usually the delta reflects the probability that the OTM option will be ITM, so I am not sure what is ...

View answer