Tool GWR for Multiple Predictors (Shapes)

Geographically Weighted Regression for multiple predictors. Regression details are stored in a copy of the input data set. If the input data set is not a point data set, the feature centroids are used as spatial reference.

References

Fotheringham, S.A., Brunsdon, C., Charlton, M. (2002): Geographically Weighted Regression: the analysis of spatially varying relationships. John Wiley & Sons. online.
Fotheringham, S.A., Charlton, M., Brunsdon, C. (1998): Geographically weighted regression: a natural evolution of the expansion method for spatial data analysis. Environment and Planning A 30(11), 1905â€“1927. online.
Lloyd, C. (2010): Spatial Data Analysis - An Introduction for GIS Users. Oxford, 206p.
Zhang, D., Ren, N., and Hou, X. (2018): An improved logistic regression model based on a spatially weighted technique (ILRBSWT v1.0) and its application to mineral prospectivity mapping. Geosci. Model Dev., 11, 2525-2539. doi:10.5194/gmd-11-2525-2018.

Author: O.Conrad (c) 2010
Menu: Spatial and Geostatistics|Geographically Weighted Regression

Parameters

	Name	Type	Identifier	Description	Constraints
Input	Shapes	shapes, input	`POINTS`	-	-
Output	Regression	shapes, output	`REGRESSION`	-	-
Options	Dependent Variable	table field	`DEPENDENT`	-	-
	Predictors	table fields	`PREDICTORS`	-	-
	Logistic Regression	boolean	`LOGISTIC`	-	Default: 0
	Weighting Function	choice	`DW_WEIGHTING`	-	Available Choices: [0] no distance weighting [1] inverse distance to a power [2] exponential [3] gaussian Default: 0
	Power	floating point number	`DW_IDW_POWER`	-	Minimum: 0.000000 Default: 2.000000
	Bandwidth	floating point number	`DW_BANDWIDTH`	Bandwidth for exponential and Gaussian weighting	Minimum: 0.000000 Default: 1.000000
	Search Range	choice	`SEARCH_RANGE`	-	Available Choices: [0] local [1] global Default: 1
	Maximum Search Distance	floating point number	`SEARCH_RADIUS`	local maximum search distance given in map units	Minimum: 0.000000 Default: 1000.000000
	Number of Points	choice	`SEARCH_POINTS_ALL`	-	Available Choices: [0] maximum number of nearest points [1] all points within search distance Default: 1
	Minimum	integer number	`SEARCH_POINTS_MIN`	minimum number of points to use	Minimum: 1 Default: 16
	Maximum	integer number	`SEARCH_POINTS_MAX`	maximum number of nearest points	Minimum: 1 Default: 20

Command-line

Usage: saga_cmd statistics_regression 7 [-POINTS <str>] [-DEPENDENT <str>] [-PREDICTORS <str>] [-REGRESSION <str>] [-LOGISTIC <str>] [-DW_WEIGHTING <str>] [-DW_IDW_POWER <double>] [-DW_BANDWIDTH <double>] [-SEARCH_RANGE <str>] [-SEARCH_RADIUS <double>] [-SEARCH_POINTS_ALL <str>] [-SEARCH_POINTS_MIN <num>] [-SEARCH_POINTS_MAX <num>]
  -POINTS:<str>           	Shapes
	shapes, input
  -DEPENDENT:<str>        	Dependent Variable
	table field
  -PREDICTORS:<str>       	Predictors
	table fields
  -REGRESSION:<str>       	Regression
	shapes, output
  -LOGISTIC:<str>         	Logistic Regression
	boolean
	Default: 0
  -DW_WEIGHTING:<str>     	Weighting Function
	choice
	Available Choices:
	[0] no distance weighting
	[1] inverse distance to a power
	[2] exponential
	[3] gaussian
	Default: 0
  -DW_IDW_POWER:<double>  	Power
	floating point number
	Minimum: 0.000000
	Default: 2.000000
  -DW_BANDWIDTH:<double>  	Bandwidth
	floating point number
	Minimum: 0.000000
	Default: 1.000000
  -SEARCH_RANGE:<str>     	Search Range
	choice
	Available Choices:
	[0] local
	[1] global
	Default: 1
  -SEARCH_RADIUS:<double> 	Maximum Search Distance
	floating point number
	Minimum: 0.000000
	Default: 1000.000000
  -SEARCH_POINTS_ALL:<str>	Number of Points
	choice
	Available Choices:
	[0] maximum number of nearest points
	[1] all points within search distance
	Default: 1
  -SEARCH_POINTS_MIN:<num>	Minimum
	integer number
	Minimum: 1
	Default: 16
  -SEARCH_POINTS_MAX:<num>	Maximum
	integer number
	Minimum: 1
	Default: 20