whether the calculation results in the MGWR and GWR4 are the same?

pysal / mgwr

Multiscale Geographically Weighted Regression (MGWR)

https://mgwr.readthedocs.io/

BSD 3-Clause "New" or "Revised" License

368 stars 126 forks source link

whether the calculation results in the MGWR and GWR4 are the same? #92

Closed binbin110 closed 3 years ago

binbin110 commented 3 years ago

when i use MGWR software to calculate GWR , it will report an error "ERROR:root:Matrix is singular.". But if i use GWR4 to run used the same data, it can run. i want to know, whether the calculation results in the two software are the same?

Ziqi-Li commented 3 years ago

Hello @binbin110,

It may be slightly different if you use golden-section search since the lower and upper bound are different than theses in GWR4 (well, I suspect this, but I don't have access to the code in GWR4). The results should be consistent if you use a pre-defined bandwidth. If you do see other differences, feel free to attach a copy of the data, I could look into this.

Cheers, Ziqi

binbin110 commented 3 years ago

Hello @Ziqi-Li ，

Thanks for your reply. When i use MGWR software(golden-section) to calculate GWR , it will report an error, as the picture, error .When i use the pre-defined bandwidth( last bandwith in error) to calculate ,it can run . Whether the last bandwith in the error is the best bandwidth ? whether i can use the bandwith(the last bandwith in error) to calculate?

Best regards， Jianbin