I am getting different results for the same data set when I used both mgwr from pysal and the MGWR software, why?

[firatgundem]

[marquisvictor]

Hi @firatgundem, are you doing any data preprocessing? did you tune any of the parameters or are they consistent in both mgwr and mgwr software?

[TaylorOshan]

did you standardize the data.... This is the default in the desktop software, but not the API.

…

On Mon, Mar 3, 2025 at 11:10 AM Victor E. Irekponor < ***@***.***> wrote: Hi @firatgundem <https://github.com/firatgundem>, are you doing any data preprocessing? did you tune any of the parameters or are they consistent in both mgwr and mgwr software? — Reply to this email directly, view it on GitHub <#159 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AB553TOR3EXJY2O2DODR67D2SR5GBAVCNFSM6AAAAABYHDG7C6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMOJUHA3TSMJUGY> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***> [image: marquisvictor]*marquisvictor* left a comment (pysal/mgwr#159) <#159 (comment)> Hi @firatgundem <https://github.com/firatgundem>, are you doing any data preprocessing? did you tune any of the parameters or are they consistent in both mgwr and mgwr software? — Reply to this email directly, view it on GitHub <#159 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AB553TOR3EXJY2O2DODR67D2SR5GBAVCNFSM6AAAAABYHDG7C6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMOJUHA3TSMJUGY> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[firatgundem]

I use standardized data. The data are subject to the same data preprocessing, and all the fine tunings are the same for both apps. The bandwidths and coefficients are different. Have you ever experienced something like this?

[TaylorOshan]

no, try not standardizing in the desktop app. And making sure all other options are the same. We cannot help any further without a replicable example/dat.

…

On Mon, Mar 3, 2025 at 2:02 PM Firat Gundem ***@***.***> wrote: I use standardized data. The data are subject to the same data preprocessing, and all the fine tunings are the same for both apps. The bandwidths and coefficients are different. Have you ever experienced something like this? — Reply to this email directly, view it on GitHub <#159 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AB553TMLS4X7J2T3A7WLOID2SSRN3AVCNFSM6AAAAABYHDG7C6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMOJVGI4TGNJUG4> . You are receiving this because you commented.Message ID: ***@***.***> [image: firatgundem]*firatgundem* left a comment (pysal/mgwr#159) <#159 (comment)> I use standardized data. The data are subject to the same data preprocessing, and all the fine tunings are the same for both apps. The bandwidths and coefficients are different. Have you ever experienced something like this? — Reply to this email directly, view it on GitHub <#159 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AB553TMLS4X7J2T3A7WLOID2SSRN3AVCNFSM6AAAAABYHDG7C6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMOJVGI4TGNJUG4> . You are receiving this because you commented.Message ID: ***@***.***>