Sharpe's (1966) portfolio performance ratio, the ratio of the portfolio’s expected return to its standard deviation, is a very well known tool for comparing portfolios. However, due to the presence of random denominators in the definition of the ratio, the sampling distribution of the Sharpe ratio is somewhat difficult to determine. This paper studies the properties of Sharpe ratio and then uses the bootstrap methodology to suggest a new “double” Sharpe ratio which incorporates estimation risk. We illustrate our methodology with the 30 largest growth mutual funds. We find that the ranking of mutual funds by the Sharpe and Double Sharpe ratios can be quite different.