We investigated motorcycle rider death rates between states with full motorcycle helmet laws and those without. This was done using both unadjusted bivariate analyses and multivariate random-effects generalized least squares regression models of rider death rates. Multivariate models were adjusted for the competing influences of several explanatory variables, including the existence of a motorcycle helmet law. From 1994 to 1996, states with helmet laws experienced a median death rate of 6.20 riders per 10 000 registered motorcycles and states without helmet laws experienced a median death rate of 5.07 riders per 10 000 registered motorcycles (P=0.008). After controlling for other factors that affect motorcycle rider fatalities (most notably...