gwer (version 3.0)

gwer.multiscale.diag: Diagnostic for Geographically Weighted Elliptical Regression Models

Description

This function obtains the values of different residuals types and calculates the diagnostic measures for the fitted geographically weighted elliptical regression model.

Usage

gwer.multiscale.diag(object, ...)

Arguments

object

an object with the result of the fitted multiscale geographically weighted elliptical regression model.

...

arguments to be used to form the default control argument if it is not supplied directly.

Value

Returns a list of diagnostic arrays:

ro

ordinal residuals.

rr

response residuals.

rp

pearson residuals.

rs

studentized residuals.

rd

deviance residuals.

dispersion

coefficient of dispersion parameter.

Hat

the hat matrix.

h

main diagonal of the hat matrix.

GL

generalized leverage.

GLbeta

generalized leverage of location parameters estimation.

GLphi

generalized leverage of dispersion parameters estimation.

DGbeta

cook distance of location parameters estimation.

DGphi

cook distance of dispersion parameters estimation.

Cic

normal curvature for case-weight perturbation.

Cih

normal curvature for scale perturbation.

Lmaxr

local influence on response (additive perturbation in responce).

Lmaxc

local influence on coefficients (additive perturbation in predictors).

References

Brunsdon, C., Fotheringham, A. S. and Charlton, M. E. (1996). Geographically weighted regression: a method for exploring spatial nonstationarity. Geographical analysis, 28(4), 281-298. 10.1111/j.1538-4632.1996.tb00936.x

Galea, M., Paula, G. A., and Cysneiros, F. J. A. (2005). On diagnostics in symmetrical nonlinear models. Statistics & Probability Letters, 73(4), 459-467. 10.1016/j.spl.2005.04.033

See Also

elliptical

Examples

# NOT RUN {
data(georgia, package = "spgwr")
fit.formula <- PctBach ~ TotPop90 + PctRural + PctFB + PctPov
gwer.bw.t <- bw.gwer(fit.formula, data = gSRDF, family = Student(3), adapt = TRUE)
msgwr.fit.t <- gwer.multiscale(fit.formula, family = Student(3), data = gSRDF, 
                               bws0 = rep(gwer.bw.t, 5), hatmatrix = TRUE, 
                               adaptive = TRUE)
gwer.multiscale.diag(msgwr.fit.t)
# }