We use a no-arbitrage, cost-of-carry asset pricing model to show that the existence of cointegration between spot and forward (futures) prices depends on the time-series properties of the cost-of-carry. We argue that the conditions for cointegration are more likely to hold in currency markets than in commodity markets, explaining many of the empirical results in the literature. We also use this model to demonstrate why the forward rate forecast error, the basis, and the forward premium are serially correlated, and to develop econometric tests of the "unbiasedness hypothesis" (sometimes called the "simple efficiency hypothesis") in various financial markets. The unbiasedness hypothesis is so prevalent in the finance literature that many tests for it have been developed. We examine four of the common tests and and use our cointegration results to demonstrate why each of these tests should reject the null hypothesis of unbiasedness. We find strong support for our hypothesis in the existing empirical literature.