Examining the validity of a test of futures market efficiency

In investigations of the efficiency of futures pricing, empirical estimates of fixed parameters in the model have led to the conclusion that the futures prices offer inefficient (or biased) estimates of the futures (or spot) prices at contract maturity. Maberly (1985) disagrees with this conclusion and argues that the empirical findings are the result of the application of ordinary least squares (OLS) to censored data. An attempt is made to show that Maberly's censoring argument is incorrect. The alternative explanation offered is that the results are biased because the explanatory variable is a lagged value of the dependent variable. The bias results from the correlation between the independent variable and previous values for the error term. The alternative explanation is supported with Monte Carlo evidence. There is important real-world significance to the results because several empirical studies have shown that spot prices are well approximated by a random walk process.