[R-sig-Geo] residuals of gwr and ols

Milan Sharma milansharma2012 at yahoo.com
Tue Feb 12 17:21:52 CET 2013


Dear all,
I fitted gwr and ols and I was expecting that residuals for gwr will be smaller than that of ols. But, my result  (copied below) is kind of mixed. Some ols residuals are smaller than gwr, some are not.
Is it because of small samples? or anything else?
Milan
     -0.136016648  1.101457156 -1.578367473  0.105823902  2.564813044
 [6]  2.180718179  0.045675369 -4.507514803 -1.292321914 -2.485451077
[11] -0.368047977  1.691501792  2.684117999 -0.556613862 -0.289227113
[16] -0.155533739 -0.021840369 -0.021840369  2.173046587 -3.416457929
[21]  0.151411146  0.724629941 -2.876030643  1.023334130  0.918531627
[26] -1.376270203 -2.474632837  3.183919800 -0.177862432  0.022877635
[31] -2.141706576 -0.869152125  0.319373467 -1.648694491 -2.915420257
[36]  0.116417634 -2.337159270  1.938201163  2.738647354  2.644367167
[41]  2.550086985 -1.423905997  1.982824142  1.790273664 -0.748049508
[46] -3.107517323 -3.971182584  0.681914115  3.726619604  4.143072934
[51] -2.249552558 -2.790999526 -0.005880056  1.960107982  0.604239516
[56]  0.926852572  1.894691740  1.249465628 -0.917200873 -2.698823361
[61] -1.599490524  1.874868510  2.846065630 -0.201141839  1.391264890
[66] -2.591306751
> res.adpt$SDF$gwr.e
 [1]  0.003574804  0.401173060 -0.098673920 -0.398602560  0.388960727
 [6]  1.176528697  1.249810375 -3.083140986  0.875553761 -2.149192311
[11] -0.104606457 -0.027614179  0.571800125 -2.374157297  0.742099604
[16]  0.287192964 -0.250966065 -0.402284402  0.189696242 -1.393609850
[21]  0.051342940  0.566711177 -1.692136783  1.043811603 -0.771654807
[26] -0.055346083  0.122587447  1.031404349  0.173498890 -0.033888702
[31] -0.301781064 -0.189544419 -0.148000181 -1.282745180 -1.208561844
[36]  0.499945507 -0.199431072  0.152781739  0.351565548  3.161790009
[41] -0.105187439  0.166309039  0.581371048 -0.140668745 -0.982077223
[46] -0.657665352 -1.891088552 -0.496321984  1.332209404  1.874694434
[51]  0.079247599 -1.043226527  0.523089114  0.420164685  0.021321941
[56]  1.907471032  1.183379281  2.591380013 -0.333712724 -0.996557548
[61] -0.214775620 -0.266639348  0.208623714  0.367054376 -0.013960720
[66]  0.196095634




More information about the R-sig-Geo mailing list