Mgcv has a hard time if your independent smooth variables are anything but randomly distributed. Honestly, I would just use a random forest. Then all the interactions are naturally incorporated and you aren't committing to linear relationships with lat and long.
How are you fitting your GAM? Maybe some regularization is needed? Are you wedded to GAM? A Random Forest would be self regularizing within the sample outcome ranges.
Kind of a shot in the dark, but does anyone have any connections who do homeowner's insurance that I could speak with on the phone? I don't want to buy, I just want to ask some questions about the process to someone who doesn't have motives.
Happy to release this blog post demonstrating an end-to-end workflow for qualitative text analysis using ChatGPT classifications, openAI embeddings to uncover hidden topic via clustering, and context summarization with Claude2. All in #rstats.
www.azandisresearch.com/2023/10/05/t...
If you can't afford the application, you definitely can't afford grad school salaries.
Tell me who to follow to make this not true.
