r - R_number of pairs for each lag in a Variogram -

i using geor package spatial interpolation of rainfall. have tell quite new geostatistics. video tutorials in youtube, understood (well, think so) theory behind variogram. per understanding, number of pairs should decrease increasing lag distances. eg, if consider 100m long stretch (say 100m long cross section of river bed) number of pairs 5m lag 20 , number of pairs 10m lag 10 , on. kind of confused output variog function in georpackage. example given below

mydata           x      y        [1,] 415720 432795 2.551415 [2,] 415513 432834 2.553177 [3,] 415325 432740 2.824652 [4,] 415356 432847 2.751844 [5,] 415374 432858 2.194091 [6,] 415426 432774 2.598897 [7,] 415395 432811 2.699066 [8,] 415626 432762 2.916368 

this dataset a variable (rainfall intensity) , x, y coordinates of points. varigram calculation shown below

geodata=as.geodata(data,header=true) variogram=variog(geodata,coords=geodata$coords,data=geodata$data) variogram[1:3] $u [1]  46.01662 107.37212 138.04987 199.40537 291.43861 352.79411  $v [1] 0.044636453 0.025991469 0.109742986 0.029081575 0.006289056 0.041963076  $n [1] 3 8 3 3 3 2 

where

u: vector distances.

v: vector estimated variogram values @ distances given in u.

n: number of pairs in each bin

according this, number of pairs (n) have random pattern whereas corresponding lag distance (u) increasing. find hard understand this. can explain happening? suggestions/advice improve variogram calculation application (spatial interpolation of rainfall intensity) highly appreciated new geostatistics. in advance.

on linear transect of 100 m 5 m regular spacing between observations, if you'd have 20 pairs @ 5 m lag, you'd have 19 pairs @ 10 m lag. idea not hold data, because irregularly distributed, , distributed on 2 dimensions. irregularly distributed data, have few point pairs short distances. advice obtaining better looking variogram work larger data set: geostatistics starts getting interesting 30 observations, , fun on 100 observations.