Advances in Meteorology / 2015 / Article / Tab 2

Research Article

Interpolation of Missing Precipitation Data Using Kernel Estimations for Hydrologic Modeling

Table 2

Chi-square () test with Friedman method for finding difference among six infilling methods. SD represents standard deviation. value means significance probability.
(a) 4-NN

MeanSDMin.Max. valueMean rank value

Ep19−1.294.46−15.505.762.53 55.6020.0000
Qu19−1.425.03−15.067.512.74
Tw19−1.645.37−14.908.132.58
Tc19−1.185.06−14.878.294.47
Co19−1.404.69−15.426.082.68
Reg192.765.42−13.4714.386.00

(b) 6-NN

MeanSDMin.Max. valueMean rank value

Ep19−2.614.72−16.681.581.53 66.5190.0000
Qu19−2.274.71−16.202.823.16
Tw19−2.184.84−15.894.063.79
Tc19−2.154.63−16.202.844.21
Co19−2.544.69−16.591.502.32
Reg190.064.97−15.487.336.00

(c) 8-NN

MeanSDMin.Max. valueMean rank value

Ep19−3.405.04−17.331.941.32 75.8120.0000
Qu19−3.104.75−16.900.453.21
Tw19−2.744.79−16.591.294.58
Tc19−2.934.77−16.961.513.68
Co19−3.284.93−17.251.852.21
Reg19−1.245.35−16.498.086.00

(Ep: Epanechnikov, Qu: Quartic, Tw: Triweight, Tc: Tricube, Co: Cosine, and Reg: regression).