Quantitative Finance Stack Exchange is a question and answer site for finance professionals and academics. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

i'm following the "Computational Investing 1" course at Coursera.org, I was affascinated by the Beta arbitrage of CAPM

Video: https://class.coursera.org/compinvesting1-002/lecture/view?lecture_id=119

It shows, that if I found Betas and weights, I could make profit in Bearish and bullish markets. Strategy: SHORT for the Higher Beta, and LONG for Lower beta.

Is that really works? What are the bad scenarios? What he didn't say?

enter image description here

Do you know some code in R or Python, that calculate Betas? Someone has already applied this theory?

share|improve this question

This is in essence the idea behind Andrea Frazzini's paper 'Betting Against Beta'. There are various ETFs that aim to exploit the premium.

In R, you can do just do a linear regression using the lm(Y~X) which includes an intercept or using lm(Y~X+0) which regresses without an intercept. Assuming you've saved the model in variable lm.r, then to get the coefficients, you simply coef(lm.r).

In package PerformanceAnalytics, there are built in functions whereby you can just plug in the parameters, independent and dependent and risk free rate to give out the coefficients.

For python, you should take a look in the pandas package for regression analysis. Last time I checked its inside the package but was being moved to stats-model package for reasons beyond me.

Hope that helps

share|improve this answer

you can simply use excel using "single index model"

share|improve this answer
That's a solution for Excel and if I Google it it seems you have to do a fair bit of work, down-voted. – Bob Jansen May 13 '14 at 16:44

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.