Flexible discriminant techniques for forecasting clear-air turbulence .

Discusses how forecasting aircraft turbulence is based on a system of observations by pilots combined with a mostly subjective evaluation of turbulence indices derived from numerical weather prediction models. Improvements in the forecasting capability of the single indices; Use of a nonparametric multidimensional regression model and discriminant analysis to the resulting predicted values; Characteristics of a paradigm of flexible discriminant analysis (FDA); Suggestions for operational forecasts.