Disertasi dengan semua uji asumsi termasuk uji stasioner, prosection independen, setelah itu heterogenitas
Hanya di panel statis
library(readxl)
## Warning: package 'readxl' was built under R version 4.6.2
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.6.2
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyr)
## Warning: package 'tidyr' was built under R version 4.6.2
library(stringr)
## Warning: package 'stringr' was built under R version 4.6.2
library(plm)
## Warning: package 'plm' was built under R version 4.6.2
##
## Attaching package: 'plm'
## The following objects are masked from 'package:dplyr':
##
## between, lag, lead
library(lmtest)
## Warning: package 'lmtest' was built under R version 4.6.2
## Loading required package: zoo
## Warning: package 'zoo' was built under R version 4.6.2
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
library(car)
## Warning: package 'car' was built under R version 4.6.2
## Loading required package: carData
## Warning: package 'carData' was built under R version 4.6.2
##
## Attaching package: 'car'
## The following object is masked from 'package:dplyr':
##
## recode
library(tseries)
## Warning: package 'tseries' was built under R version 4.6.2
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
file_path <- "C:/Users/Lenovo/Downloads/Tugas data 15 Negara_Rianti palombu.xlsx"
raw_data <- read_excel(file_path, sheet = "Data")
kode_indikator <- c(
"NY.GDP.MKTP.KD.ZG",
"TG.VAL.TOTL.GD.ZS",
"NV.AGR.TOTL.ZS",
"NV.IND.TOTL.ZS"
)
df_panel <- raw_data %>%
filter(`Series Code` %in% kode_indikator) %>%
pivot_longer(
cols = matches("\\[YR[0-9]{4}\\]$"),
names_to = "tahun_raw",
values_to = "nilai_raw",
values_transform = list(nilai_raw = as.character)
) %>%
mutate(
negara = as.factor(`Country Name`),
kode_negara = as.factor(`Country Code`),
tahun = as.integer(str_extract(tahun_raw, "[0-9]{4}")),
nilai = suppressWarnings(as.numeric(na_if(str_trim(nilai_raw), "..")))
) %>%
select(negara, kode_negara, tahun, `Series Code`, nilai) %>%
pivot_wider(
names_from = `Series Code`,
values_from = nilai
) %>%
transmute(
negara = negara,
tahun = tahun,
y = NY.GDP.MKTP.KD.ZG,
x1 = TG.VAL.TOTL.GD.ZS,
x2 = NV.AGR.TOTL.ZS,
x3 = NV.IND.TOTL.ZS
) %>%
drop_na()
pdata <- pdata.frame(df_panel, index = c("negara", "tahun"), drop.index = FALSE)
pdim(pdata)
## Unbalanced Panel: n = 15, T = 23-25, N = 372
summary(df_panel[, c("y", "x1", "x2", "x3")])
## y x1 x2 x3
## Min. :-12.016 Min. : 16.95 Min. : 0.02462 Min. :10.58
## 1st Qu.: 2.431 1st Qu.: 40.26 1st Qu.: 2.12010 1st Qu.:27.11
## Median : 4.704 Median : 60.47 Median : 8.87297 Median :33.61
## Mean : 4.450 Mean : 83.55 Mean :10.65797 Mean :34.76
## 3rd Qu.: 6.752 3rd Qu.:111.14 3rd Qu.:14.62238 3rd Qu.:38.73
## Max. : 14.520 Max. :343.49 Max. :57.06919 Max. :76.43
vars_uji <- c("y", "x1", "x2", "x3")
for (v in vars_uji) {
cat("\n=== Pesaran CD Test:", v, "===\n")
print(pcdtest(pdata[[v]], test = "cd"))
}
##
## === Pesaran CD Test: y ===
##
## Pesaran CD test for cross-sectional dependence in panels
##
## data: pdata[[v]]
## z = 22.902, p-value < 2.2e-16
## alternative hypothesis: cross-sectional dependence
##
##
## === Pesaran CD Test: x1 ===
##
## Pesaran CD test for cross-sectional dependence in panels
##
## data: pdata[[v]]
## z = 6.4067, p-value = 1.487e-10
## alternative hypothesis: cross-sectional dependence
##
##
## === Pesaran CD Test: x2 ===
##
## Pesaran CD test for cross-sectional dependence in panels
##
## data: pdata[[v]]
## z = 25.384, p-value < 2.2e-16
## alternative hypothesis: cross-sectional dependence
##
##
## === Pesaran CD Test: x3 ===
##
## Pesaran CD test for cross-sectional dependence in panels
##
## data: pdata[[v]]
## z = 3.5778, p-value = 0.0003465
## alternative hypothesis: cross-sectional dependence
has_cips <- exists("cipstest", where = asNamespace("plm"), mode = "function")
for (v in vars_uji) {
cat("\n=== Uji Stasioneritas:", v, "===\n")
if (has_cips) {
print(tryCatch(
plm::cipstest(pdata[[v]], lags = 1, type = "intercept"),
error = function(e) e$message
))
}
print(tryCatch(
purtest(pdata[[v]], test = "ips", exo = "intercept", lags = "AIC"),
error = function(e) e$message
))
}
##
## === Uji Stasioneritas: y ===
## [1] "'arg' should be one of \"trend\", \"drift\", \"none\""
## [1] "NA/NaN/Inf in foreign function call (arg 6)"
##
## === Uji Stasioneritas: x1 ===
## [1] "'arg' should be one of \"trend\", \"drift\", \"none\""
## [1] "NA/NaN/Inf in foreign function call (arg 6)"
##
## === Uji Stasioneritas: x2 ===
## [1] "'arg' should be one of \"trend\", \"drift\", \"none\""
## [1] "NA/NaN/Inf in foreign function call (arg 6)"
##
## === Uji Stasioneritas: x3 ===
## [1] "'arg' should be one of \"trend\", \"drift\", \"none\""
## [1] "NA/NaN/Inf in foreign function call (arg 6)"
pooltest(y ~ x1 + x2 + x3, data = pdata, model = "within")
##
## F statistic
##
## data: y ~ x1 + x2 + x3
## F = 1.9123, df1 = 42, df2 = 312, p-value = 0.001044
## alternative hypothesis: unstability
summary(pvcm(y ~ x1 + x2 + x3, data = pdata, model = "within"))
## Oneway (individual) effect No-pooling model
##
## Call:
## pvcm(formula = y ~ x1 + x2 + x3, data = pdata, model = "within")
##
## Unbalanced Panel: n = 15, T = 23-25, N = 372
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -14.0821 -0.7167 0.1904 1.0804 7.7482
##
## Coefficients:
## (Intercept) x1 x2 x3
## Min. :-53.114 Min. :-0.193705 Min. :-298.15051 Min. :-1.15084
## 1st Qu.:-14.971 1st Qu.:-0.038124 1st Qu.: -0.66565 1st Qu.:-0.04347
## Median : -5.156 Median :-0.007968 Median : -0.01387 Median : 0.29891
## Mean : -3.639 Mean : 0.020100 Mean : -18.85125 Mean : 0.30885
## 3rd Qu.: 4.228 3rd Qu.: 0.024834 3rd Qu.: 0.50856 3rd Qu.: 0.48315
## Max. : 58.739 Max. : 0.480274 Max. : 14.16437 Max. : 1.52898
##
## Total Sum of Squares: 2893300
## Residual Sum of Squares: 2047.7
## Multiple R-Squared: 0.99929
cem <- plm(y ~ x1 + x2 + x3, data = pdata, model = "pooling")
fem <- plm(y ~ x1 + x2 + x3, data = pdata, model = "within")
rem <- plm(y ~ x1 + x2 + x3, data = pdata, model = "random")
pFtest(fem, cem)
##
## F test for individual effects
##
## data: y ~ x1 + x2 + x3
## F = 8.7887, df1 = 14, df2 = 354, p-value < 2.2e-16
## alternative hypothesis: significant effects
phtest(fem, rem)
##
## Hausman Test
##
## data: y ~ x1 + x2 + x3
## chisq = 7.7223, df = 3, p-value = 0.05211
## alternative hypothesis: one model is inconsistent
plmtest(cem, type = "bp")
##
## Lagrange Multiplier Test - (Breusch-Pagan)
##
## data: y ~ x1 + x2 + x3
## chisq = 171.97, df = 1, p-value < 2.2e-16
## alternative hypothesis: significant effects
summary(fem)
## Oneway (individual) effect Within Model
##
## Call:
## plm(formula = y ~ x1 + x2 + x3, data = pdata, model = "within")
##
## Unbalanced Panel: n = 15, T = 23-25, N = 372
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -15.054 -0.991 0.350 1.464 9.277
##
## Coefficients:
## Estimate Std. Error t-value Pr(>|t|)
## x1 0.0197045 0.0073575 2.6782 0.007748 **
## x2 0.3414071 0.0470384 7.2581 2.506e-12 ***
## x3 0.0296275 0.0464514 0.6378 0.524005
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 3182.4
## Residual Sum of Squares: 2574.8
## R-Squared: 0.19092
## Adj. R-Squared: 0.15207
## F-statistic: 27.8446 on 3 and 354 DF, p-value: 3.4464e-16
pbgtest(fem)
##
## Breusch-Godfrey/Wooldridge test for serial correlation in panel models
##
## data: y ~ x1 + x2 + x3
## chisq = 68.009, df = 23, p-value = 2.458e-06
## alternative hypothesis: serial correlation in idiosyncratic errors
ols_fe <- lm(y ~ x1 + x2 + x3 + factor(negara), data = df_panel)
bptest(ols_fe)
##
## studentized Breusch-Pagan test
##
## data: ols_fe
## BP = 41.596, df = 17, p-value = 0.0007669
pcdtest(fem, test = "cd")
##
## Pesaran CD test for cross-sectional dependence in panels
##
## data: y ~ x1 + x2 + x3
## z = 19.028, p-value < 2.2e-16
## alternative hypothesis: cross-sectional dependence
vif(lm(y ~ x1 + x2 + x3, data = df_panel))
## x1 x2 x3
## 1.028926 1.081271 1.058720
res_mod <- as.numeric(residuals(fem))
shapiro.test(res_mod)
##
## Shapiro-Wilk normality test
##
## data: res_mod
## W = 0.90362, p-value = 1.263e-14
jarque.bera.test(res_mod)
##
## Jarque Bera Test
##
## data: res_mod
## X-squared = 681.06, df = 2, p-value < 2.2e-16
coeftest(fem, vcov = function(x) vcovSCC(x, type = "HC0", cluster = "group"))
##
## t test of coefficients:
##
## Estimate Std. Error t value Pr(>|t|)
## x1 0.0197045 0.0049032 4.0187 7.152e-05 ***
## x2 0.3414071 0.0520606 6.5579 1.935e-10 ***
## x3 0.0296275 0.0515351 0.5749 0.5657
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1