Lab for Lecture 8: Optimal Asset Allocation

The complete portfolio and constrained optimization

1 Finding the Optimal Complete Portfolio

1.1 Data

Use the asset_class_returns.xlsx dataset with the same four asset classes as in Lecture 7: S&P 500 (sp500), 10-year Treasury bonds (tbond10), gold (gold), and real estate (real_estate), plus the T-bill rate (tbill).

Column Name Data
sp500 Annual returns on S&P 500 (includes dividends)
tbond10 Annual returns on US T. Bonds (10-year)
gold Annual percentage change in gold prices
real_estate Average annual price appreciation in residential real estate
tbill Average 3-month T.Bill rate per year

1.2 Analysis

Building on the tangency portfolio from Lecture 7:

  • Calculate the expected return, standard deviation, and Sharpe ratio of the tangency portfolio.
  • Compare the Sharpe ratio of the tangency portfolio to the Sharpe ratios of the individual assets.
  • Calculate the optimal complete portfolio for different levels of risk aversion:
    • Using the optimal capital allocation formula, calculate the weight in the tangency portfolio (versus T-bills) for investors with risk aversion coefficients \(A\) = 1, 2, 3, 4, 5, and 6.
    • For each value of \(A\), calculate the final weight in each of the four risky assets and in T-bills.
    • Report the expected return and standard deviation of each complete portfolio.
  • Solve the problem with constrained optimization (using Solver in Excel):
    • Re-solve for the tangency portfolio weights with the constraint that all weights must be non-negative (no short selling allowed) and no asset in the portfolio can have a weight larger than 30%.
    • Report the new optimal weights and compare the Sharpe ratio of this constrained tangency portfolio to the unconstrained version.
    • Calculate the optimal complete portfolio for \(A\) = 4 using the constrained tangency portfolio.

1.3 Questions

  • How does the Sharpe ratio of the tangency portfolio compare to the best individual asset’s Sharpe ratio? What does this tell you about the value of diversification?
  • How does the allocation to T-bills change as risk aversion increases? At what level of risk aversion does an investor hold more than 50% in T-bills?
  • Compare the final asset weights for an investor with \(A = 2\) versus \(A = 5\). How do the portfolios differ in terms of their composition and risk-return characteristics?
  • How much does the Sharpe ratio decline when you impose the optimization constraints?
  • The optimal allocation depends on your risk aversion coefficient. How confident are you in your own estimate of \(A\)? How sensitive are the results to small changes in this parameter?
  • If you were advising a client who is 30 years from retirement versus one who is 5 years from retirement, how might you adjust the risk aversion coefficient, and what would be the impact on their optimal allocation?
  • What are some practical considerations (beyond what we’ve modeled) that might lead you to deviate from the mathematically optimal allocation?