REGION OF INFLUENCE REGRESSION FOR ESTIMATING THE 50-YEAR FLOOD AT UNGAGED SITES

Five methods of developing regional regression models to estimate floo d characteristics at ungaged sites in Arkansas are examined. The metho ds differ in the manner in which the State is divided into subregions. Each successive method (A to E) is computationally more complex than the previous method. Method A makes no subdivision. Methods B and C de fine two and four geographic subregions, respectively. Method D uses c luster/discriminant analysis to define subregions on the basis of simi larities in watershed characteristics. Method E, the new region of inf luence method, defines a unique subregion for each ungaged site. Split -sample results indicate that, in terms of root-mean-square error meth od E (38 percent error) is best. Methods C and D (42 and 41 percent er ror) were in a virtual tie for second, and methods B (44 percent error ) and A (49 percent error) were fourth and fifth best.