1

Why does including latitude and longitude in a GAM account for spatial autocorrelation?

This thread is about how applying a smoother to longitude and latitude is a respectable method to deal with spatial autocorrelation.

I have an old-school professor who thinks this is nonsense, and that the only viable way is to model the correlation using a covariance structure imposed on residuals $\epsilon$.

I told him about the cross validated thread above, and he didn't took a look at it, claiming that there's a lot of wrong things said on forums like these.

So, now I am just looking for a better source: a book, an article, anything, which makes a good case for above claim. Any help?

  • Why don't you ask your professor to justify his argument. It's better to rebut the argument than his sources. What's to say he doesn't come back and say, "That's a terrible journal. Nothing in there is ever accurate." Look at his reasoning. Once you determine that, you'll be well on your way to offer a refutation. That's my two cents. – StatsStudent May 21 '17 at 00:05
  • This would go better as a comment in that thread. Setting aside the contention between you and your professor, you are asking for literature references. You don't have enough reputation to comment, but if you asked in an answer for a reference, the answer would be converted to a comment fairly quickly. That is a little clumsy but a thread with title such as "Source to prove professor wrong?" is not itself informative to others and you don't seem to be asking a new question. – Nick Cox May 21 '17 at 10:13

0 Answers0