Journal of Applied Sciences1812-56541812-5662Asian Network for Scientific Information10.3923/jas.2008.3242.3248JouP. HaghighatAkhoond-AliA.M.BehniaA.ChinipardazR.122008818This study is devoted to compare the goodness of fitting
of the monthly precipitation for five old raingauge stations (Bushehr,
Isfahan, Meshed, Tehran and Jask) in Iran using parametric and nonparametric
methods. The parametric methods include normal, two and three parameter
log-normal, two parameter gamma, Pearson and log-Pearson type III and
Gumbel extreme value type I distributions. The nonparametric approach
is Gaussian (normal) kernel function. The smoothing parameter were calculated
by four methods including rule of thumb, Adamowski criterion, least squares
cross-validation and Sheater and Jones plug-in. Results from the least
squares cross-validation were better comparing to other methods due to
goodness of fit tests applied in this study. The results of this study
showed that the monthly precipitation data fitted to the parametric methods
much better than nonparametric method.]]>Adamowski, K.,1989Adamowski, K.,1996Adamowski, K.,2000Behnia, A.K. and P.H. Jou,2007Bowman, A.,1985Faucher, D., P.F. Rasmussen and B. Bobee,2002Gingras, D. and K. Adamowski,1992Guo, S.L.,1991Haan, C.T., 1977Karmakar, S. and S.P. Simonovic,2008Kim, K.D. and J.H. Heo,2002Kite, G.W.,1988Lall, U., Y.I. Moon and K. Bosworth,1993Moon, Y.I., U. Lall and K. Bosworth,1993Park, B.U. and J.S. Marron,1990Rao, A.R. and K.H. Hamed,1999Rudemo, M.,1982Sheater, S.J. and M.C. Jones,1991Silverman, B.W.,1986