Type: Package
Title: Hierarchical Partitioning of R2 for Spatial Simultaneous Autoregressive Model
Version: 0.0-1
Date: 2025-8-22
Depends: R (≥ 3.4.0),spatialreg,ggplot2,vegan
Imports: spdep
Maintainer: Jiangshan Lai <lai@njfu.edu.cn>
Description: Conducts hierarchical partitioning to calculate individual contributions of spatial and predictors (groups) towards total R2 for spatial simultaneous autoregressive model.
License: GPL-2 | GPL-3 [expanded from: GPL]
Encoding: UTF-8
RoxygenNote: 7.3.1
NeedsCompilation: no
Packaged: 2025-08-22 06:05:33 UTC; lai
Author: Jiangshan Lai ORCID iD [aut, cre]
Repository: CRAN
Date/Publication: 2025-08-27 16:30:07 UTC

Internal function for glmm.hp() to create diagonal matrix

Description

Internal function for glmm.hp() to create diagonal matrix

Usage

creatbin(col, binmatrix)

Arguments

col

Imput number.

binmatrix

Imput empty matrix.

Value

a matrix

a matix

A diagonal matrix

Internal function for glmm.hp()

Description

Internal function for glmm.hp()

Usage

genList(ivlist, value)

Arguments

ivlist

The names of explanatory variable.

value

The sequence ID.

Value

a vector

newlist

A vector for variable index.

Calculate Nagelkerke pseudo R-squared for a linear model

Description

This function computes the Nagelkerke pseudo R-squared for a linear model ('lm' object) by comparing the log-likelihood of the fitted model to that of the null model (intercept-only).

Usage

nagelkerke_r2_lm(model)

Arguments

model

An object of class lm.

Details

Nagelkerke R² is a normalized version of the likelihood ratio R², scaled to have a maximum of 1. It is commonly used for generalized linear models but can also be applied to linear models.

The formula used is:

R^2_{Nagelkerke} = \frac{1 - \exp\left(\frac{2}{n} (LL_{null} - LL_{model})\right)}{1 - \exp\left(\frac{2}{n} LL_{null}\right)}

where LL_{model} is the log-likelihood of the fitted model and LL_{null} is the log-likelihood of the null model.

Value

A numeric value representing the Nagelkerke pseudo R-squared.

References

Nagelkerke, N. J. D. (1991). A note on a general definition of the coefficient of determination. Biometrika, 78(3), 691–692.

Examples

data(mtcars)
fit <- lm(mpg ~ wt + hp, data = mtcars)
nagelkerke_r2_lm(fit)

Internal function for glmm.hp() to determine whether the odd number

Description

Internal function for glmm.hp() to determine whether the odd number

Usage

odd(val)

Arguments

val

Imput number.

Value

a logical value

Logical value

TRUE or FALSE

Plot for a spatialreg.hp object

Description

Plot for a spatialreg.hp object

Usage

## S3 method for class 'spatialreghp'
plot(x, plot.perc = FALSE, commonality = FALSE, color = NULL, dig = 4, ...)

Arguments

x

A spatialreg.hp object.

plot.perc

Logical;if TRUE, the bar plot (based on ggplot2 package) of the percentage to individual effects of variables and spatial towards total explained variation, the default is FALSE to show plot with original individual effects.

commonality

Logical; If TRUE, the result of commonality analysis is shown, the default is FALSE.

color

Color of variables.

dig

Integer; number of decimal places in Venn diagram.

...

unused

Value

a ggplot object

Author(s)

Jiangshan Lai lai@njfu.edu.cn

Examples

library(spatialreg)
library(spdep)
data(oldcol, package="spdep")
listw <- spdep::nb2listw(COL.nb, style="W")
ev <- eigenw(listw)
W <- as(listw, "CsparseMatrix")
trMatc <- trW(W, type="mult")
COL.lag.eig <- lagsarlm(CRIME ~ INC + HOVAL, data=COL.OLD, listw=listw,
method="eigen", control=list(pre_eig=ev, OrdVsign=1))
spatialreg.hp(COL.lag.eig)
spatialreg.hp(COL.lag.eig,iv=list(pre1="INC",pre2="HOVAL"))
spatialreg.hp(COL.lag.eig,iv=list(pre1="INC",pre2="HOVAL"),commonality=TRUE)
plot(spatialreg.hp(COL.lag.eig))
plot(spatialreg.hp(COL.lag.eig,commonality=TRUE),commonality=TRUE)

Hierarchical Partitioning of R2 for Spatial Simultaneous Autoregressive Model

Description

Hierarchical Partitioning of R2 for Spatial Simultaneous Autoregressive Model

Usage

spatialreg.hp(mod, iv = NULL, commonality = FALSE)

Arguments

mod

Fitted spatialreg objects.

iv

optional The relative importance of predictor groups will be assessed. The input for iv should be a list, where each element contains the names of variables belonging to a specific group. These variable names must correspond to the predictor variables defined in the model (mod).

commonality

Logical; If TRUE, the result of commonality analysis is shown, the default is FALSE.

Details

This function conducts hierarchical partitioning to calculate the individual contributions of spatial and each predictor towards total R2 from spatialreg package for spatial simultaneous autoregressive model.

Value

Total.R2

The R2 for the full model.

commonality.analysis

If commonality=TRUE, a matrix containing the value and percentage of all commonality (2^N-1 for N predictors or matrices).

Individual.R2

A matrix containing individual effects and percentage of individual effects for spatial and each predictor

Author(s)

Jiangshan Lai lai@njfu.edu.cn

References

Examples

library(spatialreg)
library(spdep)
data(oldcol, package="spdep")
listw <- spdep::nb2listw(COL.nb, style="W")
ev <- eigenw(listw)
W <- as(listw, "CsparseMatrix")
trMatc <- trW(W, type="mult")
COL.lag.eig <- lagsarlm(CRIME ~ INC + HOVAL, data=COL.OLD, listw=listw,
method="eigen", control=list(pre_eig=ev, OrdVsign=1))
spatialreg.hp(COL.lag.eig)
spatialreg.hp(COL.lag.eig,iv=list(pre1="INC",pre2="HOVAL"))
spatialreg.hp(COL.lag.eig,iv=list(pre1="INC",pre2="HOVAL"),commonality=TRUE)
COL.errW.eig <- errorsarlm(CRIME ~ INC + HOVAL, data=COL.OLD,
listw, control=list(pre_eig=ev))
spatialreg.hp(COL.errW.eig)
spatialreg.hp(COL.errW.eig,iv=list(pre1="INC",pre2="HOVAL"))
spatialreg.hp(COL.errW.eig,iv=list(pre1="INC",pre2="HOVAL"),commonality=TRUE)