Take a moment to predict

  • Tiago Moraes Castel-Branco (Student)

Student thesis: Master's Thesis


We analyze option-implied and realized variance, skewness and kurtosis, as well as their differences (also called risk premia) as predictors of market returns and of the cross section of stock returns. We find that the variance risk premium is the only variable capable of predicting the S&P 500 index returns, with a monthly out-of-sample R2 above 6% for the period 2001-2014. However, all analyzed variables have shown to be useful in predicting the cross section of stock returns. Self-financed portfolios long on the least exposed stocks to the market variable and short on the most exposed stocks achieve significant Carhart 4-factor Jenson’s alphas and perform considerably better (up to twice as good) than the S&P 500 index in terms of Sharpe ratio, with positive skewness.
Date of Award4 Nov 2015
Original languageEnglish
Awarding Institution
  • Universidade Católica Portuguesa
SupervisorJosé Faias (Supervisor)


  • Mestrado em Economia

Cite this