Conditional distribution in portfolio theory

We present a new method to obtain a conditional mean vector and it conditio nal covariance matrix when given an investor's view about return profiles o f certain assets. The method extends earlier results that were limited to t he conditional mean. The new method allows an investor to express views on return means, volatilities, and correlations. An application of our results illustrates how a single anticipated volatility shock spreads to other ass ets and increases the correlation coefficients among assets. Another applic ation shows how a flight-to-quality Event affects volatilities and correlat ions. Based on the conditional mean and covariance matrix, we then derive a nalytically an optimal mean-variance portfolio and discuss its implications for asset allocation.