Tugas Praktikum 11
A. Model Prediksi GRP Data China
Deskripsi Data china_join
1. Persiapan Data
# Load Package
suppressPackageStartupMessages({
library(sf)
library(readxl)
library(tidyverse)
library(ggplot2)
library(spdep)
library(spatialreg)
library(MuMIn)
library(patchwork)
})
# Membaca data spasial dalam format shapefile (.shp)
shp_china <- st_read("D:\\SEM 5\\RegSpas\\data china\\China29")## Reading layer `China29' from data source `D:\SEM 5\RegSpas\data china\China29' using driver `ESRI Shapefile'
## Simple feature collection with 29 features and 12 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 73.5577 ymin: 20.22264 xmax: 134.7739 ymax: 53.56086
## Geodetic CRS: WGS 84
data_china <- read_excel("D:\\SEM 5\\RegSpas\\Data_China.xlsx")
china_join <- shp_china %>%
left_join(data_china,
by = c("NAME_1" = "Region"))
head(china_join)## Simple feature collection with 6 features and 16 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 92.76416 ymin: 20.22264 xmax: 120.8376 ymax: 42.77393
## Geodetic CRS: WGS 84
## ID_0 ISO NAME_0 ID_1 NAME_1 HASC_1 CCN_1 CCA_1 TYPE_1 ENGTYPE_1
## 1 49 CHN China 1 Anhui CN.AH 0 <NA> Sh?ng Province
## 2 49 CHN China 2 Beijing CN.BJ 0 <NA> ZhÃxiáshì Municipality
## 3 49 CHN China 3 Chongqing CN.CQ 0 <NA> ZhÃxiáshì Municipality
## 4 49 CHN China 4 Fujian CN.FJ 0 <NA> Sh?ng Province
## 5 49 CHN China 5 Gansu CN.GS 0 <NA> Sh?ng Province
## 6 49 CHN China 6 Guangdong CN.GD 0 <NA> Sh?ng Province
## NL_NAME_1 VARNAME_1 Long Lat GRP Level_of_Urbanization
## 1 ??|?? ?nhu? 117.2262 31.82579 28792 46.50
## 2 ??|?? B?ij?ng 116.4107 40.18491 87475 86.20
## 3 ??|?? Chóngqìng 107.8748 30.05865 38914 56.98
## 4 ?? Fújià n 117.9815 26.08641 52763 59.60
## 5 ??|?? G?nsù 100.9339 37.82079 21978 38.75
## 6 ??|?? Gu?ngd?ng 113.4164 23.34225 54095 67.40
## geometry
## 1 MULTIPOLYGON (((116.4263 34...
## 2 MULTIPOLYGON (((116.6669 40...
## 3 MULTIPOLYGON (((108.5419 32...
## 4 MULTIPOLYGON (((117.689 23....
## 5 MULTIPOLYGON (((97.18472 42...
## 6 MULTIPOLYGON (((110.1182 20...
2. Eksplorasi Data
GRP <- ggplot(data = china_join) +
geom_sf(
aes(fill = GRP),
color = "white",
linewidth = 0.2
) +
scale_fill_viridis_c(
option = "magma",
name = "GRP"
) +
labs(
title = "Gross Regional Product",
subtitle = "Data kontinu per provinsi",
x = "Longitude",
y = "Latitude"
) +
theme_minimal() +
theme(
legend.position = "bottom",
plot.title = element_text(face = "bold", size = 14),
plot.subtitle = element_text(size = 11)
)
Urbanization <- ggplot(data = china_join) +
geom_sf(
aes(fill = `Level_of_Urbanization`),
color = "white",
linewidth = 0.2
) +
scale_fill_viridis_c(
option = "magma",
name = "Level of Urbanization"
) +
labs(
title = "Level of Urbanization",
subtitle = "Data kontinu per provinsi",
x = "Longitude",
y = "Latitude"
) +
theme_minimal() +
theme(
legend.position = "bottom",
plot.title = element_text(face = "bold", size = 14),
plot.subtitle = element_text(size = 11)
)
GRP | Urbanization## Classes 'sf' and 'data.frame': 29 obs. of 17 variables:
## $ ID_0 : chr "49" "49" "49" "49" ...
## $ ISO : chr "CHN" "CHN" "CHN" "CHN" ...
## $ NAME_0 : chr "China" "China" "China" "China" ...
## $ ID_1 : chr "1" "2" "3" "4" ...
## $ NAME_1 : chr "Anhui" "Beijing" "Chongqing" "Fujian" ...
## $ HASC_1 : chr "CN.AH" "CN.BJ" "CN.CQ" "CN.FJ" ...
## $ CCN_1 : chr "0" "0" "0" "0" ...
## $ CCA_1 : chr NA NA NA NA ...
## $ TYPE_1 : chr "Sh?ng" "ZhÃxiáshì" "ZhÃxiáshì" "Sh?ng" ...
## $ ENGTYPE_1 : chr "Province" "Municipality" "Municipality" "Province" ...
## $ NL_NAME_1 : chr "??|??" "??|??" "??|??" "??" ...
## $ VARNAME_1 : chr "?nhu?" "B?ij?ng" "Chóngqìng" "Fújià n" ...
## $ Long : num 117 116 108 118 101 ...
## $ Lat : num 31.8 40.2 30.1 26.1 37.8 ...
## $ GRP : num 28792 87475 38914 52763 21978 ...
## $ Level_of_Urbanization: num 46.5 86.2 57 59.6 38.8 ...
## $ geometry :sfc_MULTIPOLYGON of length 29; first list element: List of 1
## ..$ :List of 1
## .. ..$ : num [1:7291, 1:2] 116 116 116 116 116 ...
## ..- attr(*, "class")= chr [1:3] "XY" "MULTIPOLYGON" "sfg"
## - attr(*, "sf_column")= chr "geometry"
## - attr(*, "agr")= Factor w/ 3 levels "constant","aggregate",..: NA NA NA NA NA NA NA NA NA NA ...
## ..- attr(*, "names")= chr [1:16] "ID_0" "ISO" "NAME_0" "ID_1" ...
## ID_0 ISO NAME_0
## 0 0 0
## ID_1 NAME_1 HASC_1
## 0 0 0
## CCN_1 CCA_1 TYPE_1
## 0 29 0
## ENGTYPE_1 NL_NAME_1 VARNAME_1
## 0 0 0
## Long Lat GRP
## 0 0 0
## Level_of_Urbanization geometry
## 0 0
3. Regresi OLS
##
## Call:
## lm(formula = GRP ~ Level_of_Urbanization, data = china_join)
##
## Residuals:
## Min 1Q Median 3Q Max
## -12050.9 -4410.4 -374.8 2961.6 14948.1
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -31895.5 5197.6 -6.137 1.48e-06 ***
## Level_of_Urbanization 1400.0 92.6 15.118 1.06e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 6595 on 27 degrees of freedom
## Multiple R-squared: 0.8944, Adjusted R-squared: 0.8904
## F-statistic: 228.6 on 1 and 27 DF, p-value: 1.064e-14
Interpretasi: Level_of_Urbanization berpengaruh positif dan signifikan terhadap GRP (p < 0,001) dengan R² = 0,894, sehingga urbanisasi menjelaskan sebagian besar variasi GRP antar provinsi.
4. Matriks Pembobot Spasial
# Baca jarak kereta dari sheet Railway Distance
rail <- read_excel("D:\\SEM 5\\RegSpas\\Data_China.xlsx", sheet = "Railway Distance", skip = 1)## New names:
## • `` -> `...1`
5. Uji Morans’I
##
## Global Moran I for regression residuals
##
## data:
## model: lm(formula = GRP ~ Level_of_Urbanization, data = china_join)
## weights: W
##
## Moran I statistic standard deviate = 1.1234, p-value = 0.1306
## alternative hypothesis: greater
## sample estimates:
## Observed Moran I Expectation Variance
## 0.010629595 -0.033552435 0.001546711
Interpretasi: Moran’s I pada sisaan OLS tidak signifikan (p = 0,131 > 0,05), sehingga sisaan tidak menunjukkan autokorelasi spasial di sepanjang jaringan kereta api.
6. Uji Lagrange Multiplier
## Please update scripts to use lm.RStests in place of lm.LMtests
## Rao's score (a.k.a Lagrange multiplier) diagnostics for spatial
## dependence
## data:
## model: lm(formula = GRP ~ Level_of_Urbanization, data = china_join)
## test weights: listw
##
## statistic parameter p.value
## RSerr 0.0277967 1 0.8676
## adjRSerr 0.0726855 1 0.7875
## RSlag 0.0035418 1 0.9525
## adjRSlag 0.0484307 1 0.8258
## SARMA 0.0762273 2 0.9626
Interpretasi: Seluruh uji LM (error, lag, robust, SARMA) tidak signifikan (p > 0,05), sehingga model spasial global (SAR, SEM, SDM) tidak diperlukan.
7. SLX Model
china.SLX <- lmSLX(GRP ~ Level_of_Urbanization, data = china_join, listw = W, Durbin = TRUE);
summary(china.SLX)##
## Call:
## lm(formula = formula(paste("y ~ ", paste(colnames(x)[-1], collapse = "+"))),
## data = as.data.frame(x), weights = weights)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -2.335e+04 4.130e+04 -5.654e-01 5.766e-01
## Level_of_Urbanization 1.387e+03 1.139e+02 1.217e+01 3.074e-12
## lag.Level_of_Urbanization -1.418e+02 6.801e+02 -2.086e-01 8.364e-01
Interpretasi: Urbanisasi provinsi itu sendiri berpengaruh positif signifikan (koefisien 1.387, p < 0,001), sedangkan lag urbanisasi tetangga tidak signifikan (p = 0,836), sehingga tidak ada bukti efek spillover.
8. LR test : SLX vs OLS Regression
## 'log Lik.' -295.1173 (df=4)
## 'log Lik.' -295.1415 (df=3)
# nilai LR
LR <- 2 * (as.numeric(logLik(china.SLX)) -
as.numeric(logLik(china.lm)))
# derajat bebas
df <- attr(logLik(china.SLX), "df") -
attr(logLik(china.lm), "df")
# p-value
pchisq(LR, df = df, lower.tail = FALSE)## [1] 0.8257453
## [1] 597.2431
## [1] 599.9012
Interpretasi: LR test tidak signifikan (p = 0,826) dan AICc OLS (597,24) lebih kecil daripada SLX (599,90), sehingga model terbaik adalah OLS.
B. Model Dependensi Spasial (Jawa Barat)
Data Kemiskinan Jawa Barat
1. Data Preprocessing
## Reading layer `Jabar2' from data source `D:\SEM 5\RegSpas\JABAR\Jabar2' using driver `ESRI Shapefile'
## Simple feature collection with 26 features and 7 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 106.3705 ymin: -7.823398 xmax: 108.8338 ymax: -5.91377
## CRS: NA
data_jabar <- read_excel("D:\\SEM 5\\RegSpas\\JABAR\\data_jabar.xlsx")
data_jabar$KABKOTNO <- as.character(data_jabar$KABKOTNO)
jabar <- shp_jabar %>%
left_join(data_jabar, by = "KABKOTNO") %>%
na.omit()
colnames(jabar)## [1] "PROVNO.x" "KABKOTNO" "KODE2010.x" "PROVINSI.x" "KABKOT.x"
## [6] "SUMBER" "IDSP2010.x" "PROVNO.y" "KODE2010.y" "PROVINSI.y"
## [11] "KABKOT.y" "IDSP2010.y" "Long" "Lat" "p.miskin15"
## [16] "p.miskin16" "j.miskin15" "j.miskin16" "AHH2015" "AHH2016"
## [21] "EYS2015" "EYS2016" "MYS2015" "MYS2016" "EXP2015"
## [26] "EXP2016" "APM.SD15" "APM.SMP15" "APM.SMA15" "APM.PT15"
## [31] "APK.SD15" "APK.SMP15" "APK.SMA15" "APK.PT15" "APS.USIA15"
## [36] "APS.USIA2" "APS.USIA3" "APS.USIA4" "geometry"
2. Exploratory Analysis
plot(jabar[,c(
"p.miskin15",
"AHH2015",
"EYS2015",
"MYS2015",
"EXP2015",
"APM.SD15",
"APM.SMP15",
"APM.SMA15",
"APM.PT15",
"APK.SD15",
"APK.SMP15",
"APK.SMA15",
"APK.PT15",
"APS.USIA15",
"APS.USIA2",
"APS.USIA3",
"APS.USIA4"
)])3. Matriks Pembobot Spasial
4. Penentuan Variabel (Indeks Moran)
# =========================================================
# ANALISIS MORAN'S I RESIDUAL
# MENCARI KOMBINASI X TERBAIK
# DENGAN P-VALUE TERKECIL
# =========================================================
# =========================================================
# 5. DAFTAR VARIABEL
# =========================================================
variabel_list <- c(
"p.miskin15",
"AHH2015",
"EYS2015",
"MYS2015",
"EXP2015",
"APM.SD15",
"APM.SMP15",
"APM.SMA15",
"APM.PT15",
"APK.SD15",
"APK.SMP15",
"APK.SMA15",
"APK.PT15",
"APS.USIA15",
"APS.USIA2",
"APS.USIA3",
"APS.USIA4"
)
# =========================================================
# 6. TENTUKAN VARIABEL Y
# =========================================================
variabel_Y <- "p.miskin15"
# variabel kandidat X
variabel_X <- setdiff(
variabel_list,
variabel_Y
)
# =========================================================
# 7. DATAFRAME HASIL
# =========================================================
hasil_model <- data.frame(
Formula = character(),
Jumlah_X = numeric(),
Moran_I = numeric(),
P_Value = numeric(),
stringsAsFactors = FALSE
)
# =========================================================
# 8. LOOP KOMBINASI VARIABEL
# =========================================================
maksimum_X <- 6
for (k in 1:maksimum_X) {
# membuat kombinasi
kombinasi_x <- combn(
variabel_X,
k,
simplify = FALSE
)
# loop tiap kombinasi
for (x_set in kombinasi_x) {
tryCatch({
# =====================================================
# MEMBUAT FORMULA
# =====================================================
formula_text <- paste(
variabel_Y,
"~",
paste(x_set, collapse = " + ")
)
rumus <- as.formula(formula_text)
# =====================================================
# MODEL OLS
# =====================================================
model_ols <- lm(
rumus,
data = jabar
)
# =====================================================
# MORAN TEST RESIDUAL
# =====================================================
uji_moran <- lm.morantest(
model_ols,
lw_jabar,
zero.policy = TRUE
)
# =====================================================
# AMBIL NILAI
# =====================================================
moran_i <- as.numeric(
uji_moran$estimate["Observed Moran I"]
)
p_val <- uji_moran$p.value
# =====================================================
# SIMPAN JIKA SIGNIFIKAN
# =====================================================
if (p_val < 0.05) {
hasil_model <- rbind(
hasil_model,
data.frame(
Formula = formula_text,
Jumlah_X = k,
Moran_I = moran_i,
P_Value = p_val
)
)
}
}, error = function(e) {
# abaikan error
NULL
})
}
}
# =========================================================
# 9. URUTKAN HASIL
# =========================================================
hasil_model <- hasil_model %>%
arrange(P_Value)
# =========================================================
# 11. MODEL TERBAIK
# P-VALUE PALING KECIL
# =========================================================
if (nrow(hasil_model) == 0) {
cat("Tidak ada model signifikan.\n")
} else {
# ambil model terbaik
model_terbaik <- hasil_model %>%
slice(1)
cat(
"Formula : ",
as.character(model_terbaik$Formula),
"\n",
sep = ""
)
cat(
"Jumlah Variabel X : ",
model_terbaik$Jumlah_X,
"\n",
sep = ""
)
cat(
"Moran's I : ",
round(model_terbaik$Moran_I, 5),
"\n",
sep = ""
)
cat(
"P-Value : ",
format(
model_terbaik$P_Value,
scientific = FALSE
),
"\n",
sep = ""
)
}## Formula : p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 + APK.PT15 + APS.USIA15
## Jumlah Variabel X : 5
## Moran's I : 0.5012
## P-Value : 0.005018003
Interpretasi: Kombinasi terbaik adalah
p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 + APK.PT15 + APS.USIA15
dengan Moran’s I = 0,5012 (p = 0,005), yang berarti sisaan OLS memiliki
autokorelasi spasial positif yang kuat sehingga perlu model regresi
spasial.
5. OLS Regression
jabar.lm <- lm(p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 + APK.PT15 + APS.USIA15, data=jabar)
summary(jabar.lm)##
## Call:
## lm(formula = p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 + APK.PT15 +
## APS.USIA15, data = jabar)
##
## Residuals:
## Min 1Q Median 3Q Max
## -6.2541 -1.5129 0.7468 1.7253 2.9766
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -263.5186 236.1804 -1.116 0.2883
## EYS2015 2.7220 2.1113 1.289 0.2238
## APM.SD15 -0.5289 0.6939 -0.762 0.4619
## APK.SD15 0.4526 0.2946 1.536 0.1527
## APK.PT15 -0.3228 0.1731 -1.865 0.0891 .
## APS.USIA15 2.4849 2.5164 0.987 0.3446
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.114 on 11 degrees of freedom
## Multiple R-squared: 0.5749, Adjusted R-squared: 0.3816
## F-statistic: 2.975 on 5 and 11 DF, p-value: 0.06127
6. Uji Lagrange Multiplier
## Please update scripts to use lm.RStests in place of lm.LMtests
## Rao's score (a.k.a Lagrange multiplier) diagnostics for spatial
## dependence
## data:
## model: lm(formula = p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 +
## APK.PT15 + APS.USIA15, data = jabar)
## test weights: listw
##
## statistic parameter p.value
## RSerr 7.23955 1 0.007132 **
## adjRSerr 5.48939 1 0.019132 *
## RSlag 2.01129 1 0.156133
## adjRSlag 0.26113 1 0.609346
## SARMA 7.50067 2 0.023510 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Interpretasi: RSerr (p = 0,007) dan adjRSerr (p = 0,019) signifikan, sedangkan RSlag dan adjRSlag tidak signifikan. Dependensi spasial bersumber dari komponen error, bukan lag variabel dependen.
7. Spatial Error Model (SEM)
jabar.err <- errorsarlm(p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 + APK.PT15 + APS.USIA15,lw_jabar,data=jabar, zero.policy = TRUE)
summary(jabar.err)##
## Call:errorsarlm(formula = p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 +
## APK.PT15 + APS.USIA15, data = jabar, listw = lw_jabar, zero.policy = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.96720 -0.97706 0.17825 0.76731 1.45103
##
## Type: error
## Regions with no neighbours included:
## 18 19 21 25 26
## Coefficients: (asymptotic standard errors)
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -425.458866 84.564213 -5.0312 4.874e-07
## EYS2015 4.311729 1.035451 4.1641 3.126e-05
## APM.SD15 -1.521207 0.226462 -6.7173 1.852e-11
## APK.SD15 0.640932 0.101930 6.2880 3.216e-10
## APK.PT15 -0.358322 0.069408 -5.1626 2.436e-07
## APS.USIA15 4.680477 0.828208 5.6513 1.592e-08
##
## Lambda: 0.9059, LR test value: 23.088, p-value: 1.5476e-06
## Asymptotic standard error: 0.060606
## z-value: 14.947, p-value: < 2.22e-16
## Wald statistic: 223.43, p-value: < 2.22e-16
##
## Log likelihood: -28.18863 for error model
## ML residual variance (sigma squared): 1.0473, (sigma: 1.0234)
## Number of observations: 17
## Number of parameters estimated: 8
## AIC: 72.377, (AIC for lm: 93.465)
Interpretasi: Lambda = 0,906 sangat signifikan dan semua variabel X signifikan pada model SEM. AIC SEM (72,377) jauh lebih kecil daripada OLS (93,465).
8. Model SLX
jabar.SLX <- lmSLX(p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 + APK.PT15 + APS.USIA15,lw_jabar,data=jabar, zero.policy = TRUE, Durbin = TRUE);
summary(jabar.SLX)##
## Call:
## lm(formula = formula(paste("y ~ ", paste(colnames(x)[-1], collapse = "+"))),
## data = as.data.frame(x), weights = weights)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -145.59982 307.35728 -0.47372 0.65245
## EYS2015 2.63817 4.59362 0.57431 0.58663
## APM.SD15 0.26488 0.97666 0.27122 0.79532
## APK.SD15 0.59059 0.23882 2.47293 0.04827
## APK.PT15 -0.20577 0.38277 -0.53759 0.61021
## APS.USIA15 0.36388 3.17195 0.11472 0.91241
## lag.EYS2015 -4.02200 9.31944 -0.43157 0.68113
## lag.APM.SD15 3.42980 1.21392 2.82538 0.03014
## lag.APK.SD15 -0.41090 0.69159 -0.59414 0.57412
## lag.APK.PT15 0.38003 0.82137 0.46268 0.65990
## lag.APS.USIA15 -2.48727 1.03245 -2.40910 0.05264
Interpretasi: Lag variabel X umumnya tidak berpengaruh signifikan, sehingga SDEM tidak diperlukan dan SEM sudah cukup.
9. Model SARMA
jabar.sarma <- sacsarlm(p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 + APK.PT15 + APS.USIA15,lw_jabar, data=jabar, zero.policy = TRUE)
summary(jabar.sarma)##
## Call:sacsarlm(formula = p.miskin15 ~ EYS2015 + APM.SD15 + APK.SD15 +
## APK.PT15 + APS.USIA15, data = jabar, listw = lw_jabar, zero.policy = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.837342 -0.900247 -0.050073 0.685523 1.606525
##
## Type: sac
## Coefficients: (asymptotic standard errors)
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -442.074286 83.148799 -5.3167 1.057e-07
## EYS2015 4.793132 1.140231 4.2037 2.626e-05
## APM.SD15 -1.707710 0.293038 -5.8276 5.623e-09
## APK.SD15 0.672837 0.103147 6.5231 6.886e-11
## APK.PT15 -0.392055 0.076727 -5.1097 3.226e-07
## APS.USIA15 4.939024 0.838588 5.8897 3.869e-09
##
## Rho: 0.20377
## Asymptotic standard error: 0.19972
## z-value: 1.0202, p-value: 0.30761
## Lambda: 0.91256
## Asymptotic standard error: 0.065071
## z-value: 14.024, p-value: < 2.22e-16
##
## LR test value: 23.918, p-value: 6.4015e-06
##
## Log likelihood: -27.77358 for sac model
## ML residual variance (sigma squared): 0.97176, (sigma: 0.98578)
## Number of observations: 17
## Number of parameters estimated: 9
## AIC: 73.547, (AIC for lm: 93.465)
Interpretasi: Rho (0,204) tidak signifikan (p = 0,308), sedangkan Lambda (0,913) sangat signifikan, sehingga SEM lebih tepat dibanding SARMA.
10. LR Test : SEM vs SARMA
## Model df AIC logLik Test L.Ratio p-value
## jabar.err 1 8 72.377 -28.189 1
## jabar.sarma 2 9 73.547 -27.774 2 0.83008 0.36225
Interpretasi: L.Ratio = 0,830 (p = 0,362) sehingga gagal tolak H0. Penambahan parameter rho tidak meningkatkan model secara signifikan dan AIC SEM (72,377) lebih kecil dari SARMA (73,547).
11. Akaike Information Criterion Corrected (AICc)
## [1] 105.9096
## [1] 90.37725
## [1] 99.26145
Interpretasi: AICc SEM (90,377) paling kecil dibanding SARMA (99,261) dan OLS (105,910), sehingga model terbaik untuk data kemiskinan Jawa Barat adalah SEM.
C. Model Dependensi Spasial (Materi Tambahan)
Package
library(spdep) # Analisis data spasial: spatial autocorrelation, spatial regression
library(sp) # Struktur data untuk manipulasi data spasial (poligon, titik, dll)
library(sf) # Mengelola data spasial dengan standar Simple Features (sf)
library(readxl) # Membaca file Excel (format .xls dan .xlsx)
library(openxlsx) # Membuat, membaca, dan menulis file Excel (lebih cepat dari readxl)
library(corrplot) # Membuat visualisasi korelasi dalam bentuk plot## corrplot 0.95 loaded
library(DescTools) # Kumpulan fungsi statistik deskriptif dan inferensial
library(nortest) # Melakukan uji normalitas (Anderson-Darling, Lilliefors, dll)
library(car) # Fungsi regresi linear dan diagnostik model (vif, durbinWatsonTest, dll)## Loading required package: carData
##
## Attaching package: 'car'
## The following object is masked from 'package:DescTools':
##
## Recode
## The following object is masked from 'package:dplyr':
##
## recode
## The following object is masked from 'package:purrr':
##
## some
library(spatialreg) # Estimasi model regresi spasial (SAR, SEM, SLM)
library(lmtest) # Fungsi untuk menguji model regresi (heteroskedastisitas, serial correlation)## Loading required package: zoo
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
Import Data
## ID_KAB PROPINSI KAB long lat y x1 x2
## 1 3101 DKI JAKARTA KEPULAUAN SERIBU 106.4933 -5.796823 27.35 89.5 50.0
## 2 3171 DKI JAKARTA JAKARTA SELATAN 106.8100 -6.272549 36.22 103.1 52.5
## 3 3172 DKI JAKARTA JAKARTA TIMUR 106.9003 -6.255373 27.46 90.3 48.7
## 4 3173 DKI JAKARTA JAKARTA PUSAT 106.8351 -6.181230 29.17 88.5 54.9
## 5 3174 DKI JAKARTA JAKARTA BARAT 106.7483 -6.165469 32.16 99.6 48.1
## 6 3175 DKI JAKARTA JAKARTA UTARA 106.8695 -6.129185 32.67 102.2 45.8
## [1] 119 8
## Reading layer `jawa' from data source `D:\SEM 5\RegSpas\Dataset 06\Jawamap' using driver `ESRI Shapefile'
## Simple feature collection with 119 features and 5 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 105.0998 ymin: -8.78036 xmax: 116.2702 ymax: -5.048857
## Geodetic CRS: WGS 84
## Simple feature collection with 119 features and 5 fields
## Geometry type: MULTIPOLYGON
## Dimension: XY
## Bounding box: xmin: 105.0998 ymin: -8.78036 xmax: 116.2702 ymax: -5.048857
## Geodetic CRS: WGS 84
## First 10 features:
## PROVNO KABKOTNO PROVINSI KABKOT ID2013
## 1 31 01 DKI JAKARTA KEPULAUAN SERIBU 3101
## 2 31 71 DKI JAKARTA JAKARTA SELATAN 3171
## 3 31 72 DKI JAKARTA JAKARTA TIMUR 3172
## 4 31 73 DKI JAKARTA JAKARTA PUSAT 3173
## 5 31 74 DKI JAKARTA JAKARTA BARAT 3174
## 6 31 75 DKI JAKARTA JAKARTA UTARA 3175
## 7 32 01 JAWA BARAT BOGOR 3201
## 8 32 02 JAWA BARAT SUKABUMI 3202
## 9 32 03 JAWA BARAT CIANJUR 3203
## 10 32 04 JAWA BARAT BANDUNG 3204
## geometry
## 1 MULTIPOLYGON (((106.3842 -5...
## 2 MULTIPOLYGON (((106.8491 -6...
## 3 MULTIPOLYGON (((106.9719 -6...
## 4 MULTIPOLYGON (((106.8788 -6...
## 5 MULTIPOLYGON (((106.711 -6....
## 6 MULTIPOLYGON (((106.969 -6....
## 7 MULTIPOLYGON (((106.994 -6....
## 8 MULTIPOLYGON (((106.9652 -6...
## 9 MULTIPOLYGON (((107.2843 -6...
## 10 MULTIPOLYGON (((107.75 -6.8...
Eksplorasi Data
Mengecek Missing Value
## [1] ID_KAB PROPINSI KAB long lat y x1 x2
## <0 rows> (or 0-length row.names)
Interpretasi: Tidak terdapat missing value pada data.
Ringkasan Statistik Deskriptif
## KAB long lat y
## Length:119 Min. :105.8 Min. :-8.365 Min. :13.72
## Class :character 1st Qu.:107.9 1st Qu.:-7.653 1st Qu.:22.07
## Mode :character Median :110.2 Median :-7.258 Median :25.40
## Mean :110.0 Mean :-7.199 Mean :25.53
## 3rd Qu.:111.8 3rd Qu.:-6.820 3rd Qu.:29.20
## Max. :114.2 Max. :-5.797 Max. :36.22
## x1 x2
## Min. : 80.10 Min. :25.10
## 1st Qu.: 87.25 1st Qu.:33.20
## Median : 92.20 Median :41.20
## Mean : 93.04 Mean :40.78
## 3rd Qu.: 99.85 3rd Qu.:49.25
## Max. :105.00 Max. :55.00
# Menunjukkan kab/kota dengan Y tertinggi
kab_max <- data %>%
arrange(desc(y)) %>%
slice(1)
print(paste("Kabupaten/kota dengan Y tertinggi adalah", kab_max$KAB))## [1] "Kabupaten/kota dengan Y tertinggi adalah JAKARTA SELATAN"
# Menunjukkan kab/kota dengan Y terendah
kab_min <- data %>%
arrange(y) %>%
slice(1)
print(paste("Kabupaten/kota dengan Y terendah adalah", kab_min$KAB))## [1] "Kabupaten/kota dengan Y terendah adalah KLATEN"
Interpretasi: Y tertinggi adalah Kota Jakarta Selatan (36,22), Y terendah adalah Kabupaten Klaten (13,72), dengan rata-rata Y sebesar 25,53.
Boxplot - Identifikasi Pencilan
par(mfrow=c(1,3))
boxplot(data$y,main = "Sebaran Y", col="dodgerblue")
boxplot(data$x1,main = "Sebaran X1", col="dodgerblue")
boxplot(data$x2,main = "Sebaran X2", col="dodgerblue")Interpretasi: Tidak terdapat pencilan pada Y, X1, maupun X2.
Hubungan antara Peubah Respon dan Peubah Penjelas
Interpretasi: X1 dan X2 berhubungan linear positif dengan Y (X1 lebih kuat), dan antar peubah penjelas tidak berhubungan.
Korelasi antar Peubah
## long lat y x1
## long 1.00000000 -0.74541782 -0.1306153 -0.08974212
## lat -0.74541782 1.00000000 0.1679668 0.07479095
## y -0.13061532 0.16796681 1.0000000 0.80963262
## x1 -0.08974212 0.07479095 0.8096326 1.00000000
Uji Korelasi Y dengan X1
##
## Pearson's product-moment correlation
##
## data: data$y and data$x1
## t = 14.921, df = 117, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.7370471 0.8637532
## sample estimates:
## cor
## 0.8096326
Uji Korelasi Y dengan X2
##
## Pearson's product-moment correlation
##
## data: data$y and data$x2
## t = 6.5822, df = 117, p-value = 1.374e-09
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.3749256 0.6399554
## sample estimates:
## cor
## 0.5198398
Interpretasi: X1 dan X2 berkorelasi positif dengan Y (0,81 dan 0,51), keduanya signifikan pada taraf 5%, dan antar peubah penjelas tidak berkorelasi sehingga multikolinearitas kecil kemungkinannya.
Sebaran Spasial Data
Sebaran Spasial Y
k=101
colfunc <- colorRampPalette(c("green", "yellow","red"))
peta$y <- data$y
# Plot menggunakan ggplot2
ggplot(peta) +
geom_sf(aes(fill = y)) +
scale_fill_gradientn(colors = colfunc(k)) +
labs(title = "Peta Sebaran Spasial Peubah Respon Y") +
theme_minimal()Sebaran Spasial X1
peta$x1<- data$x1
# Plot menggunakan ggplot2
ggplot(peta) +
geom_sf(aes(fill = x1)) +
scale_fill_gradientn(colors = colfunc(k)) +
labs(title = "Sebaran Spasial Peubah Penjelas X1") +
theme_minimal()Sebaran Spasial X2
peta$x2<- data$x2
# Plot menggunakan ggplot2
ggplot(peta) +
geom_sf(aes(fill = x2)) +
scale_fill_gradientn(colors = colfunc(k)) +
labs(title = "Sebaran Spasial Peubah Penjelas X2") +
theme_minimal()Interpretasi: Y cenderung bergerombol dengan wilayah tetangganya, mengindikasikan autokorelasi spasial positif.
Matriks Pembobot Spasial
Matriks Bobot Berdasarkan Ketetanggan
Queen Contiguity
# Memvalidasi geometri dalam objek sf
peta <- st_make_valid(peta)
# Konversi objek sf ke objek sp
sp.peta <- as(peta, "Spatial")
# Mengakses slot polygons dari objek sp
sp.polygons <- SpatialPolygons(sp.peta@polygons)
queen <- poly2nb(sp.peta, queen = T)## Neighbour list object:
## Number of regions: 119
## Number of nonzero links: 522
## Percentage nonzero weights: 3.68618
## Average number of links: 4.386555
## 1 region with no links:
## 1
## 3 disjoint connected subgraphs
W.queen <- nb2listw(queen, style='W',zero.policy=TRUE)
qc = moran.test(data$y, W.queen,randomisation=T,
alternative="greater", zero.policy = TRUE)
qc##
## Moran I test under randomisation
##
## data: data$y
## weights: W.queen
## n reduced by no-neighbour observations
##
## Moran I statistic standard deviate = 1.3921, p-value = 0.08195
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.085984133 -0.008547009 0.004611252
##
## Monte-Carlo simulation of Moran I
##
## data: data$y
## weights: W.queen
## number of simulations + 1: 100
##
## statistic = 0.085984, observed rank = 97, p-value = 0.03
## alternative hypothesis: greater
Rook Contiguity
## Neighbour list object:
## Number of regions: 119
## Number of nonzero links: 518
## Percentage nonzero weights: 3.657934
## Average number of links: 4.352941
## 1 region with no links:
## 1
## 3 disjoint connected subgraphs
W.rook <- nb2listw(rook, style='W',zero.policy=TRUE)
rc = moran.test(data$y, W.rook,randomisation=T,
alternative="greater", zero.policy = TRUE)
rc##
## Moran I test under randomisation
##
## data: data$y
## weights: W.rook
## n reduced by no-neighbour observations
##
## Moran I statistic standard deviate = 1.5987, p-value = 0.05495
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.100243070 -0.008547009 0.004630949
##
## Monte-Carlo simulation of Moran I
##
## data: data$y
## weights: W.rook
## number of simulations + 1: 100
##
## statistic = 0.10024, observed rank = 94, p-value = 0.06
## alternative hypothesis: greater
Matriks Bobot Berdasarkan Jarak
# Ekstrak koordinat centroid
longlat <- st_coordinates(centroids)
# Tambahkan koordinat long dan lat ke objek peta
peta$long <- longlat[, 1] # Kolom X (long)
peta$lat <- longlat[, 2] # Kolom Y (lat)coords <- peta[c("long","lat")]
#class(coords)
koord <- as.data.frame(coords)
jarak<-dist(longlat, method = "euclidean")
m.jarak<-as.matrix(jarak)K-Nearest Neighbor
# k = 5
W.knn<-knn2nb(knearneigh(longlat,k=5,longlat=TRUE))
W.knn.s <- nb2listw(W.knn,style='W')
MI.knn <- moran(data$y,W.knn.s,n=length(W.knn.s$neighbours),S0=Szero(W.knn.s))
mt1 = moran.test(data$y,W.knn.s,randomisation = T,alternative = "greater")
mt1##
## Moran I test under randomisation
##
## data: data$y
## weights: W.knn.s
##
## Moran I statistic standard deviate = 2.1802, p-value = 0.01462
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.107628130 -0.008474576 0.002835976
Radial Distance Weight
W.rdw <-dnearneigh(longlat,0,105,longlat=TRUE)
W.rdw.s <- nb2listw(W.rdw,style='W')
MI.rdw <- moran(data$y,W.rdw.s,n=length(W.rdw.s$neighbours),S0=Szero(W.rdw.s))
mt2 = moran.test(data$y,W.rdw.s,randomisation = T,alternative = "greater")
mt2##
## Moran I test under randomisation
##
## data: data$y
## weights: W.rdw.s
##
## Moran I statistic standard deviate = 0.82869, p-value = 0.2036
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.0148447999 -0.0084745763 0.0007918598
Invers Distance Weight
alpha1=1
W.idw <-1/(m.jarak^alpha1)
diag(W.idw)<-0
rtot<-rowSums(W.idw,na.rm=TRUE)
W.idw.sd<-W.idw/rtot #row-normalized
W.idw.s = mat2listw(W.idw.sd,style='W')
MI.idw <- moran(data$y,W.idw.s,n=length(W.idw.s$neighbours),S0=Szero(W.idw.s))
mt3 = moran.test(data$y,W.idw.s,randomisation = T,alternative = "greater")
mt3##
## Moran I test under randomisation
##
## data: data$y
## weights: W.idw.s
##
## Moran I statistic standard deviate = 2.3687, p-value = 0.008925
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.040533196 -0.008474576 0.000428063
alpha2=2
W.idw2<-1/(m.jarak^alpha2)
diag(W.idw2)<-0
rtot<-rowSums(W.idw2,na.rm=TRUE)
W.idw2.sd<-W.idw2/rtot #row-normalized
W.idw2.s = mat2listw(W.idw2.sd,style='W')
MI.idw2 <- moran(data$y,W.idw2.s,n=length(W.idw2.s$neighbours),S0=Szero(W.idw2.s))
mt4 = moran.test(data$y,W.idw2.s,randomisation = T,alternative = "greater")
mt4##
## Moran I test under randomisation
##
## data: data$y
## weights: W.idw2.s
##
## Moran I statistic standard deviate = 1.9574, p-value = 0.02515
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.088273381 -0.008474576 0.002442892
Exponential Distance Weight
alpha=1
W.edw<-exp((-alpha)*m.jarak)
diag(W.edw)<-0
rtot<-rowSums(W.edw,na.rm=TRUE)
W.edw.sd<-W.edw/rtot #row-normalized
W.edw.s = mat2listw(W.edw.sd,style='W')
MI.edw <- moran(data$y,W.edw.s,n=length(W.edw.s$neighbours),S0=Szero(W.edw.s))
mt5 = moran.test(data$y,W.edw.s,randomisation = T,alternative = "greater")
mt5##
## Moran I test under randomisation
##
## data: data$y
## weights: W.edw.s
##
## Moran I statistic standard deviate = 1.3022, p-value = 0.09643
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.0099060556 -0.0084745763 0.0001992396
alpha2=2
W.edw2<-exp((-alpha2)*m.jarak)
diag(W.edw2)<-0
rtot<-rowSums(W.edw2,na.rm=TRUE)
W.edw2.sd<-W.edw2/rtot #row-normalized
W.edw2.s = mat2listw(W.edw2.sd,style='W')
MI.edw2 <- moran(data$y,W.edw2.s,n=length(W.edw2.s$neighbours),S0=Szero(W.edw2.s))
mt6 = moran.test(data$y,W.edw2.s,randomisation = T,alternative = "greater")
mt6##
## Moran I test under randomisation
##
## data: data$y
## weights: W.edw2.s
##
## Moran I statistic standard deviate = 1.875, p-value = 0.03039
## alternative hypothesis: greater
## sample estimates:
## Moran I statistic Expectation Variance
## 0.0328701345 -0.0084745763 0.0004862084
Pemilihan Matriks Bobot Terbaik
MatriksBobot <- c("K-Nearest Neighbor (k=5)",
"Radial Distance Weight (dmax=60)",
"Invers Distance Weight (alpha=1)",
"Invers Distance Weight (alpha=2)",
"Exponential Distance Weight (alpha=1)",
"Exponential Distance Weight (alpha=2)",
"Rook Contiguity",
"Queen Contiguity")
IndeksMoran <- c(MI.knn$I,MI.rdw$I,MI.idw$I,MI.idw2$I,MI.edw$I,MI.edw2$I,rc$estimate[1],qc$estimate[1])
pv = c(mt1$p.value,mt2$p.value,mt3$p.value,mt4$p.value,mt5$p.value,mt6$p.value,rc$p.value,qc$p.value)
Matriks = cbind.data.frame(MatriksBobot, IndeksMoran,"p-value"=pv)
colnames(Matriks) <-c("Matriks Bobot", "Indeks Moran", "p-value")
Matriks## Matriks Bobot Indeks Moran p-value
## 1 K-Nearest Neighbor (k=5) 0.107628130 0.014622303
## 2 Radial Distance Weight (dmax=60) 0.014844800 0.203639555
## 3 Invers Distance Weight (alpha=1) 0.040533196 0.008925225
## 4 Invers Distance Weight (alpha=2) 0.088273381 0.025147563
## 5 Exponential Distance Weight (alpha=1) 0.009906056 0.096426630
## 6 Exponential Distance Weight (alpha=2) 0.032870135 0.030394142
## 7 Rook Contiguity 0.100243070 0.054948820
## 8 Queen Contiguity 0.085984133 0.081948463
## Matriks Bobot Indeks Moran p-value
## 1 K-Nearest Neighbor (k=5) 0.10762813 0.014622303
## 3 Invers Distance Weight (alpha=1) 0.04053320 0.008925225
## 4 Invers Distance Weight (alpha=2) 0.08827338 0.025147563
## 6 Exponential Distance Weight (alpha=2) 0.03287013 0.030394142
Interpretasi: Matriks bobot dengan Indeks Moran signifikan pada taraf 5% adalah KNN (k=5), IDW (alpha=1 dan 2), dan EDW (alpha=2). KNN dengan 5 tetangga memiliki Indeks Moran tertinggi sehingga dipilih sebagai matriks bobot terbaik.
Model Regresi Klasik (OLS)
Metode OLS
##
## Call:
## lm(formula = y ~ x1 + x2, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.5977 -0.8358 0.0369 0.9222 3.5927
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -36.66154 1.72709 -21.23 <2e-16 ***
## x1 0.54223 0.01742 31.13 <2e-16 ***
## x2 0.28804 0.01447 19.90 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.392 on 116 degrees of freedom
## Multiple R-squared: 0.922, Adjusted R-squared: 0.9206
## F-statistic: 685.3 on 2 and 116 DF, p-value: < 2.2e-16
## [1] "Nilai AIC OLS 421.320527312512"
Model Diagnostics
Uji Normalitas Sisaan
##
## Anderson-Darling normality test
##
## data: err.ols
## A = 0.48312, p-value = 0.2255
Uji Kehomogenan Ragam
##
## studentized Breusch-Pagan test
##
## data: ols
## BP = 1.557, df = 2, p-value = 0.4591
Pengujian Efek Spasial
Efek Dependensi Spasial
Uji Indeks Moran
Uji Indeks Moran pada Galat Model Regresi
##
## Global Moran I for regression residuals
##
## data:
## model: lm(formula = y ~ x1 + x2, data = data)
## weights: ww
##
## Moran I statistic standard deviate = 7.7062, p-value = 1.296e-14
## alternative hypothesis: two.sided
## sample estimates:
## Observed Moran I Expectation Variance
## 0.401296232 -0.008385587 0.002826244
err.ols <- residuals(ols)
merr <- moran.test(err.ols, ww,randomisation=T,
alternative="two.sided")
merr##
## Moran I test under randomisation
##
## data: err.ols
## weights: ww
##
## Moran I statistic standard deviate = 7.7459, p-value = 9.488e-15
## alternative hypothesis: two.sided
## sample estimates:
## Moran I statistic Expectation Variance
## 0.401296232 -0.008474576 0.002798555
Uji Indeks Moran pada Peubah Y
##
## Moran I test under randomisation
##
## data: data$y
## weights: ww
##
## Moran I statistic standard deviate = 2.1802, p-value = 0.02924
## alternative hypothesis: two.sided
## sample estimates:
## Moran I statistic Expectation Variance
## 0.107628130 -0.008474576 0.002835976
Uji Indeks Moran pada Peubah X1
##
## Moran I test under randomisation
##
## data: data$x1
## weights: ww
##
## Moran I statistic standard deviate = 0.89468, p-value = 0.371
## alternative hypothesis: two.sided
## sample estimates:
## Moran I statistic Expectation Variance
## 0.039254520 -0.008474576 0.002846002
Uji Indeks Moran pada Peubah X2
##
## Moran I test under randomisation
##
## data: data$x2
## weights: ww
##
## Moran I statistic standard deviate = -1.0874, p-value = 0.2768
## alternative hypothesis: two.sided
## sample estimates:
## Moran I statistic Expectation Variance
## -0.066483348 -0.008474576 0.002845675
Peubah = c("Y", "X1", "X2", "Sisaan")
Indeks_Moran = c(my$estimate[1], mx1$estimate[1], mx2$estimate[1], merr$estimate[1])
p_value = c(my$p.value, mx1$p.value, mx2$p.value, merr$p.value)
df1 = cbind.data.frame(Peubah, Indeks_Moran, p_value)
colnames(df1) <- c("Peubah", "Indeks Moran", "p-value")
df1## Peubah Indeks Moran p-value
## 1 Y 0.10762813 2.924461e-02
## 2 X1 0.03925452 3.709605e-01
## 3 X2 -0.06648335 2.768471e-01
## 4 Sisaan 0.40129623 9.487767e-15
Interpretasi: Indeks Moran pada Y dan sisaan regresi signifikan dan bernilai positif (autokorelasi spasial positif), sedangkan pada X1 dan X2 tidak signifikan.
Uji Lagrange Multiplier
model <- lm.LMtests(ols,listw=ww,zero.policy = TRUE, test=c("LMerr","RLMerr","LMlag","RLMlag","SARMA"))## Please update scripts to use lm.RStests in place of lm.LMtests
## Rao's score (a.k.a Lagrange multiplier) diagnostics for spatial
## dependence
## data:
## model: lm(formula = y ~ x1 + x2, data = data)
## test weights: listw
##
## statistic parameter p.value
## RSerr 54.2452 1 1.770e-13 ***
## adjRSerr 31.9386 1 1.591e-08 ***
## RSlag 32.0571 1 1.497e-08 ***
## adjRSlag 9.7505 1 0.001793 **
## SARMA 63.9957 2 1.266e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Interpretasi: Uji LM (SAR, SEM, SARMA) dan robust LM signifikan pada taraf 5%, sehingga kandidat model adalah SAR, SEM, dan SARMA.
Model Regresi Spasial
Model SAR
##
## Call:lagsarlm(formula = y ~ x1 + x2, data = data, listw = ww)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.278572 -0.761564 0.016699 0.849727 2.695114
##
## Type: lag
## Coefficients: (asymptotic standard errors)
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -41.792688 1.851270 -22.575 < 2.2e-16
## x1 0.532067 0.015553 34.209 < 2.2e-16
## x2 0.290320 0.012806 22.671 < 2.2e-16
##
## Rho: 0.23233, LR test value: 25.223, p-value: 5.1057e-07
## Asymptotic standard error: 0.047605
## z-value: 4.8803, p-value: 1.0593e-06
## Wald statistic: 23.817, p-value: 1.0593e-06
##
## Log likelihood: -194.0485 for lag model
## ML residual variance (sigma squared): 1.5135, (sigma: 1.2303)
## Nagelkerke pseudo-R-squared: 0.93687
## Number of observations: 119
## Number of parameters estimated: 5
## AIC: 398.1, (AIC for lm: 421.32)
## LM test for residual autocorrelation
## test value: 7.358, p-value: 0.0066764
Uji Asumsi Model SAR
##
## Anderson-Darling normality test
##
## data: err.sar
## A = 0.28212, p-value = 0.6317
##
## studentized Breusch-Pagan test
##
## data:
## BP = 2.6875, df = 2, p-value = 0.2609
##
## Moran I test under randomisation
##
## data: err.sar
## weights: ww
##
## Moran I statistic standard deviate = 2.776, p-value = 0.005504
## alternative hypothesis: two.sided
## sample estimates:
## Moran I statistic Expectation Variance
## 0.138466721 -0.008474576 0.002801958
Interpretasi: Rho signifikan dengan AIC 398,1. Sisaan menyebar normal dan homogen, tetapi masih terdapat autokorelasi spasial pada sisaan.
Model SEM
##
## Call:errorsarlm(formula = y ~ x1 + x2, data = data, listw = ww)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.61465 -0.56031 0.16416 0.76534 2.46897
##
## Type: error
## Coefficients: (asymptotic standard errors)
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -34.736068 1.427157 -24.339 < 2.2e-16
## x1 0.523408 0.014286 36.637 < 2.2e-16
## x2 0.283754 0.011367 24.963 < 2.2e-16
##
## Lambda: 0.57406, LR test value: 33.057, p-value: 8.9503e-09
## Asymptotic standard error: 0.093935
## z-value: 6.1113, p-value: 9.8842e-10
## Wald statistic: 37.348, p-value: 9.8842e-10
##
## Log likelihood: -190.1318 for error model
## ML residual variance (sigma squared): 1.3381, (sigma: 1.1568)
## Number of observations: 119
## Number of parameters estimated: 5
## AIC: 390.26, (AIC for lm: 421.32)
Uji Asumsi Model SEM
##
## Anderson-Darling normality test
##
## data: err.sem
## A = 0.75876, p-value = 0.04711
##
## studentized Breusch-Pagan test
##
## data:
## BP = 0.89877, df = 2, p-value = 0.638
##
## Moran I test under randomisation
##
## data: err.sem
## weights: ww
##
## Moran I statistic standard deviate = -0.55031, p-value = 0.5821
## alternative hypothesis: two.sided
## sample estimates:
## Moran I statistic Expectation Variance
## -0.037483117 -0.008474576 0.002778668
Interpretasi: Lambda signifikan dengan AIC 390,26. Sisaan tidak menyebar normal, tetapi ragam homogen dan tidak ada autokorelasi spasial pada sisaan.
Model SARMA/GSM
##
## Call:
## sacsarlm(formula = y ~ x1 + x2, data = data, listw = ww, zero.policy = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.53574 -0.59853 0.10686 0.78564 2.55146
##
## Type: sac
## Coefficients: (asymptotic standard errors)
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -37.670168 2.567539 -14.672 < 2.2e-16
## x1 0.530517 0.015036 35.282 < 2.2e-16
## x2 0.286556 0.011748 24.392 < 2.2e-16
##
## Rho: 0.083991
## Asymptotic standard error: 0.064873
## z-value: 1.2947, p-value: 0.19543
## Lambda: 0.47951
## Asymptotic standard error: 0.11669
## z-value: 4.1093, p-value: 3.9689e-05
##
## LR test value: 34.119, p-value: 3.9012e-08
##
## Log likelihood: -189.6009 for sac model
## ML residual variance (sigma squared): 1.3555, (sigma: 1.1642)
## Number of observations: 119
## Number of parameters estimated: 6
## AIC: 391.2, (AIC for lm: 421.32)
Uji Asumsi Model SARMA
##
## Anderson-Darling normality test
##
## data: err.SARMA
## A = 0.70442, p-value = 0.06428
##
## studentized Breusch-Pagan test
##
## data:
## BP = 1.2851, df = 2, p-value = 0.5259
##
## Moran I test under randomisation
##
## data: err.SARMA
## weights: ww
##
## Moran I statistic standard deviate = -0.36979, p-value = 0.7115
## alternative hypothesis: two.sided
## sample estimates:
## Moran I statistic Expectation Variance
## -0.027983670 -0.008474576 0.002783258
Interpretasi: Hanya Lambda yang signifikan (Rho tidak signifikan), dengan AIC 391,2. Model SARMA memenuhi asumsi normalitas, homogenitas ragam, dan kebebasan sisaan.
Model SDM
##
## Call:lagsarlm(formula = y ~ x1 + x2, data = data, listw = ww, type = "mixed",
## zero.policy = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.460816 -0.587583 0.063713 0.803323 2.489449
##
## Type: mixed
## Coefficients: (asymptotic standard errors)
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -23.011394 5.406184 -4.2565 2.077e-05
## x1 0.528068 0.014497 36.4268 < 2.2e-16
## x2 0.287681 0.012170 23.6394 < 2.2e-16
## lag.x1 -0.226018 0.064788 -3.4886 0.0004856
## lag.x2 -0.113673 0.045416 -2.5029 0.0123175
##
## Rho: 0.52166, LR test value: 25.205, p-value: 5.1548e-07
## Asymptotic standard error: 0.10037
## z-value: 5.1973, p-value: 2.0223e-07
## Wald statistic: 27.012, p-value: 2.0223e-07
##
## Log likelihood: -188.6373 for mixed model
## ML residual variance (sigma squared): 1.3227, (sigma: 1.1501)
## Number of observations: 119
## Number of parameters estimated: 7
## AIC: 391.27, (AIC for lm: 414.48)
## LM test for residual autocorrelation
## test value: 5.7604, p-value: 0.016392
Uji Asumsi Model SDM
##
## Anderson-Darling normality test
##
## data: err.sdm
## A = 0.64985, p-value = 0.08783
qqnorm(err.sdm,datax=T)
qqline(rnorm(length(err.sdm),mean(err.sdm),sd(err.sdm)),datax=T, col="blue")##
## studentized Breusch-Pagan test
##
## data:
## BP = 2.774, df = 4, p-value = 0.5963
##
## Moran I test under randomisation
##
## data: err.sdm
## weights: ww
##
## Moran I statistic standard deviate = -0.59546, p-value = 0.5515
## alternative hypothesis: two.sided
## sample estimates:
## Moran I statistic Expectation Variance
## -0.039895217 -0.008474576 0.002784333
Goodness of Fits (Model Terbaik)
df <- data.frame("Model" = c("OLS (Regresi KlasiK)","SAR","SEM","SARMA", "SDM"),
"AIC" = c(AIC(ols),AIC(sar), AIC(sem),AIC(SARMA), AIC(sdm)))
df## Model AIC
## 1 OLS (Regresi KlasiK) 421.3205
## 2 SAR 398.0970
## 3 SEM 390.2637
## 4 SARMA 391.2017
## 5 SDM 391.2745
Interpretasi: SEM memiliki AIC terkecil tetapi sisaannya tidak normal, sehingga dipilih SARMA yang AIC-nya lebih kecil dari SAR dan OLS, hampir setara SEM, serta memenuhi seluruh asumsi sisaan.
Interpretasi dan Kesimpulan
##
## Call:
## sacsarlm(formula = y ~ x1 + x2, data = data, listw = ww, zero.policy = TRUE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -4.53574 -0.59853 0.10686 0.78564 2.55146
##
## Type: sac
## Coefficients: (asymptotic standard errors)
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -37.670168 2.567539 -14.672 < 2.2e-16
## x1 0.530517 0.015036 35.282 < 2.2e-16
## x2 0.286556 0.011748 24.392 < 2.2e-16
##
## Rho: 0.083991
## Asymptotic standard error: 0.064873
## z-value: 1.2947, p-value: 0.19543
## Lambda: 0.47951
## Asymptotic standard error: 0.11669
## z-value: 4.1093, p-value: 3.9689e-05
##
## LR test value: 34.119, p-value: 3.9012e-08
##
## Log likelihood: -189.6009 for sac model
## ML residual variance (sigma squared): 1.3555, (sigma: 1.1642)
## Number of observations: 119
## Number of parameters estimated: 6
## AIC: 391.2, (AIC for lm: 421.32)
## Impact measures (sac, exact):
## Direct Indirect Total
## x1 dy/dx 0.5311153 0.04804611 0.5791614
## x2 dy/dx 0.2868790 0.02595184 0.3128308
# Efek Umpan Balik
koef = sum$coefficients[-1]
diref = Im$direct
umbal = diref-koef
cbind.data.frame(Koefisien=koef,EfekLangsung=diref,UmpanBalik=umbal)## Koefisien EfekLangsung UmpanBalik
## x1 0.5305173 0.5311153 0.0005980484
## x2 0.2865560 0.2868790 0.0003230325
Interpretasi: Pada model SARMA, peningkatan X1 sebesar satu satuan meningkatkan Y di wilayah itu sendiri sebesar 0,531 (efek langsung), di wilayah lain 0,049 (efek tidak langsung), dan total 0,580. Untuk X2, efek langsung 0,287, tidak langsung 0,026, dan total 0,313. Efek spillover relatif kecil dibanding efek langsung.
Efek Marginal untuk Model Lainnya
## Impact measures (lag, exact):
## Direct Indirect Total
## x1 dy/dx 0.5370876 0.15600347 0.6930911
## x2 dy/dx 0.2930588 0.08512239 0.3781812
## Impact measures (mixed, exact):
## Direct Indirect Total
## x1 dy/dx 0.5339407 0.09751864 0.6314593
## x2 dy/dx 0.2920035 0.07177461 0.3637781