topic Re: Linear Regression Raster data in Imagery and Remote Sensing Questions

Linear Regression Raster data

MadhusankaJayawardhana — Mon, 10 Apr 2017 04:32:19 GMT

I have a five raster layers with same cell size and same spatial reference. I want to perform regression analyze to find out the relationship between these layers. How do I perform a regression analyze in ArcGIS? It hard to export as ASCII file because these raster images have 5000x5000 grids.

Re: Linear Regression Raster data

DanPatterson_Retired — Mon, 10 Apr 2017 06:28:45 GMT

Geographically weighted regression... from the help files

Re: Linear Regression Raster data

NeilAyres — Mon, 10 Apr 2017 06:48:17 GMT

If you wanted to do simple regression, you could create a subset using :

Create Random Points—Help | ArcGIS Desktop

and

Sample—Help | ArcGIS Desktop

Then just process the output in Excel or something.

Re: Linear Regression Raster data

DanPatterson_Retired — Mon, 10 Apr 2017 07:03:04 GMT

But in any event... heed the warning in the topic link I posted. And of course you will need data measured on an interval/ratio scale since nominal or ordinal data are not appropriate for any sort of regression analysis and you would be better performing tests of association (perhaps Chi square)

You should always begin regression analysis with Ordinary Least Squares (OLS) regression. First find a properly specified OLS model, then use the same explanatory variables to run GWR (excluding any "dummy" explanatory variables representing different spatial regimes).

Re: Linear Regression Raster data

MadhusankaJayawardhana — Mon, 10 Apr 2017 16:34:25 GMT

GWR regression works only for the feature classes. But I have a raster datasets. How do I perform GWR analyze using rasters.

Re: Linear Regression Raster data

DanPatterson_Retired — Mon, 10 Apr 2017 16:46:39 GMT

Short of converting back to vector... what are your variables? are they floating point rasters of data on an interval or ratio scale? or are they nominal/categorical data?

Re: Linear Regression Raster data

MadhusankaJayawardhana — Mon, 10 Apr 2017 16:58:04 GMT

There are four floating point rasters and one categorical raster. The attributes are rooftop surface temperature, building height, rooftop area, rooftop slope, and albedo. Rooftop aspect layer has a categorical data. These all rasters have the same spatial resolution of 0.25m.

Re: Linear Regression Raster data

DanPatterson_Retired — Mon, 10 Apr 2017 17:10:24 GMT

why not classify the rasters into categories and use Combine to produce a map showing the various combinations. These data seem more appropriate to a test of association/difference than a correlation/regression. (ie south-facing, dark surfaces will have a higher temperature, than north-facing light surfaces etc etc) I don't think you are trying to predict anything or describe the regime by an equation are you?

Re: Linear Regression Raster data

MadhusankaJayawardhana — Fri, 14 Apr 2017 00:17:49 GMT

I performed raster based multiple regression with Clark Labs Terrsat (Idrisi) software to find the correlation between above-mentioned layers. Thank you for all

Re: Linear Regression Raster data

MadhusankaJayawardhana — Fri, 14 Apr 2017 00:18:13 GMT

I performed raster based multiple regression with Clark Labs Terrsat (Idrisi) software to find the correlation between above-mentioned layers. Thank you for all

Re: Linear Regression Raster data

NakkyEkeanyanwu — Tue, 05 Apr 2022 16:43:14 GMT

Good morning. Could you walk me through the regression process in the Idrisi software? I'm also trying to run a regression with about 5 raster datasets.