I am currently employing GWR to analyze the following relationship:

average travel time of an area = distance of it from the city centre + income of an area

Further to note, correlation between time and distance is high, between time and income is low but significant. I performed an OLS and autocorrelation is seen in the residuals. Standard score is used for all the variables.

I ran the regression model in ArcGIS Pro, and a very high R2 value (0.9) results. However, it is seen that the intercepts generated by the model vary a lot (in my case, from -2 to 2) when coefficients are plotted, compared to the other two variables (distance and income) which shows reasonable ranges.

My question is - With such high variation on the intercept, how can I interpret this model (and the intercept)?

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.