plot_sp2d {pspatreg}

Plot and mapping spatial trends.

Description

Make plots and maps of the spatial trends in 2d of the objects fitted with pspatfit function.

Usage

plot_sp2d(
  object,
  data,
  coordinates = NULL,
  npoints = 300,
  cexpoints = 0.25,
  addcontour = TRUE,
  addpoints = TRUE,
  addmain = TRUE,
  addint = TRUE
)

Arguments

object

object returned from pspatfit

data

either sf or dataframe with the data.

coordinates

coordinates matrix if data is not an sf object.

npoints

number of points to use in the interpolation.

cexpoints

size of the points. Default = 0.25

addcontour

Logical value to add contour lines.

addpoints

Logical value to add spatial points to the graphics.

addmain

Add f1_main and f2_main plots in psanova case.

addint

Add f12_int in psanova case.

Value

plots and maps of the spatial trends

Author(s)

Roman Minguez	[e-mail]
Roberto Basile	[e-mail]
Maria Durban	[e-mail]
Gonzalo Espana-Heredia	[e-mail]

References

• Lee, D. and Durban, M. (2011). P-Spline ANOVA Type Interaction Models for Spatio-Temporal Smoothing. Statistical Modelling, (11), 49-69. <doi:10.1177/1471082X1001100104>

• Eilers, P. and Marx, B. (2021). Practical Smoothing. The Joys of P-Splines. Cambridge University Press.

• Fahrmeir, L.; Kneib, T.; Lang, S.; and Marx, B. (2021). Regression. Models, Methods and Applications (2nd Ed.). Springer.

• Wood, S.N. (2017). Generalized Additive Models. An Introduction with R (second edition). CRC Press, Boca Raton.

Examples

library(pspatreg)
######## EXAMPLE 2D WITH AMES DATA 
######## getting and preparing the data
library(spdep)
ames <- AmesHousing::make_ames() # Raw Ames Housing Data
ames_sf <- st_as_sf(ames, coords = c("Longitude", "Latitude"))
ames_sf$Longitude <- ames$Longitude
ames_sf$Latitude <- ames$Latitude
ames_sf$lnSale_Price <- log(ames_sf$Sale_Price)
ames_sf$lnLot_Area <- log(ames_sf$Lot_Area)
ames_sf$lnTotal_Bsmt_SF <- log(ames_sf$Total_Bsmt_SF+1)
ames_sf$lnGr_Liv_Area <- log(ames_sf$Gr_Liv_Area)
ames_sf1 <- ames_sf[(duplicated(ames_sf$Longitude) == FALSE), ]

######## formula of the model in Ames
form2d <- lnSale_Price ~ Fireplaces + Garage_Cars +
          pspl(lnLot_Area, nknots = 20) + 
          pspl(lnTotal_Bsmt_SF, nknots = 20) +
          pspl(lnGr_Liv_Area, nknots = 20) +
          pspt(Longitude, Latitude, 
               nknots = c(10, 10), 
               psanova = FALSE)

########### Constructing the spatial weights matrix
coord_sf1 <- cbind(ames_sf1$Longitude, ames_sf1$Latitude)
k5nb <- knn2nb(knearneigh(coord_sf1, k = 5, 
                          longlat = TRUE, use_kd_tree = FALSE), sym = TRUE)
lw_ames <- nb2listw(k5nb, style = "W", 
                  zero.policy = FALSE)

######## fit the model
sp2dsar <- pspatfit(form2d, data = ames_sf1, 
                    listw = lw_ames, 
                    method = "Chebyshev", 
                    type = "sar")
summary(sp2dsar)

####### plot spatial trend for spatial point coordinate
plot_sp2d(sp2dsar, data = ames_sf1)

###### MODEL WITH ANOVA DESCOMPOSITION
 form2d_psanova <- lnSale_Price ~ Fireplaces + Garage_Cars +
                   pspl(lnLot_Area, nknots = 20) + 
                   pspl(lnTotal_Bsmt_SF, nknots = 20) +
                   pspl(lnGr_Liv_Area, nknots = 20) +
                   pspt(Longitude, Latitude, 
                        nknots = c(10, 10), 
                        psanova = TRUE)
      
sp2danovasar <- pspatfit(form2d_psanova, 
                        data = ames_sf1, 
                        listw = lw_ames,
                        method = "Chebyshev", 
                        type = "sar")
summary(sp2danovasar)                         
                        
###### PLOT ANOVA DESCOMPOSITION MODEL
plot_sp2d(sp2danovasar, data = ames_sf1, 
          addmain = TRUE, addint = TRUE)