Statistical methods for estimating speed correction factors with confidence intervals for mobile source emissions models

Speed correction factors are an important component of mobile source emissi ons models. The current "ratio of means" methodology used by the California Air Resources Board (CARB) and the US EPA does not provide estimates of er ror or account for the dependence in the data. A repeated measures regressi on method that takes into account the dependence in the data and provides e stimates of error is proposed and illustrated using recent emissions data f rom CARE, A method for calculating confidence intervals for the ratio of me ans is also derived and illustrated. Using the same dataset, we find that t he method currently in use, which fits a polynomial curve to the ratio of m ean emissions: slightly underestimates the correction factors when compared with the repeated measures method. However, both methods appear to overest imate values in the middle range of speeds when compared with a method that does not assume a polynomial curve. (C) 2000 Elsevier Science Ltd. All rig hts reserved.