Regression on coordinates

DjurdjicaIvkovic — Thu, 05 Jul 2012 09:33:49 GMT

Hello everyone,

I plan to include coordinates as covariates in the regression equation in order to adjust for the spatial trend that exists in the data. After that, I want to test residuals on spatial autocorrelation in random variation. I have several questions:

1. Should I perform linear regression in which only independent variables are x and y coordinates and then tests residuals on spatial autocorrelation, or should I rather include not only coordinates as covariates but also other variables and then test residuals.

2. If I expect to have quadratic trend, and then include not only x,y, but also , xy, x squared and y squared, but then some of them (xy and y squared) have the p-value higher than the threshold --should I exclude those variables with higher p-value as being nonsignificant? How should I then interpret the trend, it is certainly not quadratic anymore?

3. I guess I should treat x and y coordinates as any other covariates, and test them on having linear relationship with dependent variable by constructing partial residual plots ... but then once I transform them (if they show they need transformation), that will not be that kind of trend any more (especially if I include xy, x squared and y squared for quadratic trend). It may show that x squared, for example, needs transformation, while x does not or so? How should I react in these situations?

Thank you.

Re: Regression on coordinates

JeffreyEvans — Thu, 05 Jul 2012 15:51:25 GMT

It sounds like regression kriging may be a suitable methods for you to explore.

http://dl.acm.org/citation.cfm?id=1294455

http://spatial-analyst.net/wiki/index.php?title=Regression-kriging_guide

http://en.wikipedia.org/wiki/Regression-kriging

topic Re: Regression on coordinates in Spatial Statistics Questions

Regression on coordinates

Re: Regression on coordinates