Hi there!
As you point out there are significant differences between the two maps you shared above, but this is because the outputs are based on two very different methodologies, standard GWR and multiscale GWR. We would not expect the two outputs to be the same. Currently, we have not implemented multiscale GWR. Our implementation of standard GWR closely matches the implementation in open source packages such as GWR4. We do not provide an option to standardize the variables within our implementation of GWR (this is done primarily for computational efficiency). We are intrigued by the multiscale GWR methodology and it is on our list of research and potential enhancements.
Documentation for the tool in ArcGIS Pro can be found here:
Geographically Weighted Regression
How Geographically Weighted Regression Works
References:
Brunsdon, C., Fotheringham, A. S., & Charlton, M. E. (1996). Geographically weighted regression: a method for exploring spatial nonstationarity. Geographical analysis, 28(4), 281-298.
Fotheringham, Stewart A., Chris Brunsdon, and Martin Charlton. Geographically Weighted Regression: the analysis of spatially varying relationships. John Wiley & Sons, 2002.
I hope this is helpful and please reach out if there are any other questions!
- Jenora D'Acosta