Input Data
library(readxl)
data.indodapoer <- read_xlsx("C:/Users/BANGSIS-1/OneDrive/Documents/indodapoer300822.xlsx")Source: https://databank.worldbank.org/source/indonesia-database-for-policy-and-economic-research#
Eksplorasi Data
colnames(data.indodapoer)## [1] "Provinces Name"
## [2] "Birth attended by Skilled Health worker (in % of total birth)"
## [3] "Capital expenditure (in IDR)"
## [4] "Education function expenditure (in IDR)"
## [5] "Environment function expenditure (in IDR)"
## [6] "Goods and services expenditure (in IDR)"
## [7] "Health function expenditure (in IDR)"
## [8] "Household Access to Electricity: Total (in % of total household)"
## [9] "Household Access to safe Sanitation (in % of total Household)"
## [10] "Household Access to Safe Water (in % of total household)"
## [11] "Household per capita expenditure (in IDR)"
## [12] "Literacy Rate for Population age 15 and over (in % of total population)"
## [13] "Monthly Per Capita Household Education Expenditure (in IDR)"
## [14] "Monthly Per Capita Household Health Expenditure (in IDR)"
## [15] "Monthly Per Capita TOTAL Household Expenditure for The Poorest 20 percent (in IDR)"
## [16] "Morbidity Rate (in %)"
## [17] "Net Enrollment Ratio: Junior Secondary (in %)"
## [18] "Net Enrollment Ratio: Primary (in %)"
## [19] "Net Enrollment Ratio: Senior Secondary (in %)"
## [20] "Others expenditure (in IDR)"
## [21] "Personnel expenditure (in IDR)"
## [22] "Public, law and order function expenditure (in IDR)"
## [23] "Total Expenditure (in IDR)"
## [24] "Total General Allocation Grant/DAU (in IDR)"
## [25] "Total Natural Resources Revenue Sharing from Fishery (in IDR, realization value)"
## [26] "Total Natural Resources Revenue Sharing from Forestry (in IDR, realization value)"
## [27] "Total Natural Resources Revenue Sharing from Gas (in IDR, realization value)"
## [28] "Total Natural Resources Revenue Sharing from Geothermal Energy (in IDR, realization value)"
## [29] "Total Natural Resources Revenue Sharing from Mining (in IDR, realization value)"
## [30] "Total Natural Resources Revenue Sharing from Oil (in IDR, realization value)"
## [31] "Total Other Revenue (in IDR)"
## [32] "Total Own Source Revenue/PAD (in IDR)"
## [33] "Total Population (in number of people)"
## [34] "Total Revenue (in IDR)"
## [35] "Total Revenue Sharing"
## [36] "Total Special Allocation Grant/DAK (in IDR)"
## [37] "Total Tax Revenue Sharing from income tax (PPh) (in IDR, realization value)"
## [38] "Total Tax Revenue Sharing from land and building tax (PBB) (in IDR, realization value)"
## [39] "Tourism and culture function expenditure (in IDR)"dim(data.indodapoer)## [1] 34 39View(data.indodapoer)
str(data.indodapoer)## tibble [34 x 39] (S3: tbl_df/tbl/data.frame)
## $ Provinces Name : chr [1:34] "Bali" "Banten" "Bengkulu" "DI Yogyakarta" ...
## $ Birth attended by Skilled Health worker (in % of total birth) : num [1:34] 99.7 91.8 97.8 100 99.3 ...
## $ Capital expenditure (in IDR) : num [1:34] 4.58e+11 9.94e+11 4.17e+11 9.41e+11 3.17e+12 ...
## $ Education function expenditure (in IDR) : num [1:34] 1.90e+12 4.30e+12 1.15e+12 1.75e+12 1.46e+13 ...
## $ Environment function expenditure (in IDR) : num [1:34] 0.00 4.00e+10 3.91e+10 4.41e+10 2.75e+12 ...
## $ Goods and services expenditure (in IDR) : num [1:34] 1.55e+12 2.18e+12 5.59e+11 7.83e+11 1.68e+13 ...
## $ Health function expenditure (in IDR) : num [1:34] 4.21e+11 6.87e+11 3.29e+11 1.77e+11 9.39e+12 ...
## $ Household Access to Electricity: Total (in % of total household) : num [1:34] 99.9 99.8 99 99.9 100 ...
## $ Household Access to safe Sanitation (in % of total Household) : num [1:34] 82.9 84.7 85.7 80.5 84.4 ...
## $ Household Access to Safe Water (in % of total household) : num [1:34] 88.4 72.5 52.3 79.9 92.8 ...
## $ Household per capita expenditure (in IDR) : num [1:34] 1509675 1517042 1140076 1411985 2257984 ...
## $ Literacy Rate for Population age 15 and over (in % of total population) : num [1:34] 96.1 100 99.9 96.3 100.6 ...
## $ Monthly Per Capita Household Education Expenditure (in IDR) : num [1:34] 75472 64586 53109 120990 121808 ...
## $ Monthly Per Capita Household Health Expenditure (in IDR) : num [1:34] 45464 32213 29649 57555 54800 ...
## $ Monthly Per Capita TOTAL Household Expenditure for The Poorest 20 percent (in IDR) : num [1:34] 520473 557254 473963 428572 795473 ...
## $ Morbidity Rate (in %) : num [1:34] 25.5 32.2 30.2 38.1 33.8 ...
## $ Net Enrollment Ratio: Junior Secondary (in %) : num [1:34] 92.9 89.3 78.5 86 84.3 ...
## $ Net Enrollment Ratio: Primary (in %) : num [1:34] 95.4 95 100.6 98 103.6 ...
## $ Net Enrollment Ratio: Senior Secondary (in %) : num [1:34] 71.6 61 68.6 71.9 60.8 ...
## $ Others expenditure (in IDR) : num [1:34] 2.75e+12 4.80e+12 6.56e+11 2.15e+12 1.55e+13 ...
## $ Personnel expenditure (in IDR) : num [1:34] 1.60e+12 1.91e+12 1.07e+12 1.56e+12 1.67e+13 ...
## $ Public, law and order function expenditure (in IDR) : num [1:34] 4.89e+10 6.02e+10 4.79e+10 4.40e+10 1.49e+12 ...
## $ Total Expenditure (in IDR) : num [1:34] 6.36e+12 9.88e+12 2.70e+12 5.43e+12 5.21e+13 ...
## $ Total General Allocation Grant/DAU (in IDR) : num [1:34] 1.20e+12 1.04e+12 1.22e+12 1.23e+12 0.00 ...
## $ Total Natural Resources Revenue Sharing from Fishery (in IDR, realization value) : num [1:34] 0.00 0.00 0.00 0.00 1.33e+09 ...
## $ Total Natural Resources Revenue Sharing from Forestry (in IDR, realization value) : num [1:34] 0.00 1.67e+08 4.08e+08 1.43e+07 1.08e+06 ...
## $ Total Natural Resources Revenue Sharing from Gas (in IDR, realization value) : num [1:34] 0.00 0.00 0.00 0.00 1.26e+10 ...
## $ Total Natural Resources Revenue Sharing from Geothermal Energy (in IDR, realization value): num [1:34] 0.00 4.69e+08 2.80e+08 0.00 0.00 ...
## $ Total Natural Resources Revenue Sharing from Mining (in IDR, realization value) : num [1:34] 0.00 2.50e+09 2.82e+10 1.61e+07 0.00 ...
## $ Total Natural Resources Revenue Sharing from Oil (in IDR, realization value) : num [1:34] 0.00 0.00 0.00 0.00 6.69e+10 ...
## $ Total Other Revenue (in IDR) : num [1:34] 8.45e+10 5.25e+10 5.50e+10 1.36e+12 1.57e+12 ...
## $ Total Own Source Revenue/PAD (in IDR) : num [1:34] 3.07e+12 5.91e+12 7.12e+11 1.88e+12 3.74e+13 ...
## $ Total Population (in number of people) : num [1:34] 4380824 13160496 2019848 3882288 10644986 ...
## $ Total Revenue (in IDR) : num [1:34] 5.72e+12 1.03e+13 2.79e+12 5.61e+12 5.59e+13 ...
## $ Total Revenue Sharing : num [1:34] 2.07e+11 7.02e+11 7.11e+10 1.14e+11 1.36e+13 ...
## $ Total Special Allocation Grant/DAK (in IDR) : num [1:34] 1.15e+12 2.63e+12 7.29e+11 1.03e+12 3.25e+12 ...
## $ Total Tax Revenue Sharing from income tax (PPh) (in IDR, realization value) : num [1:34] 2.02e+11 6.91e+11 3.87e+10 1.11e+11 1.39e+13 ...
## $ Total Tax Revenue Sharing from land and building tax (PBB) (in IDR, realization value) : num [1:34] 2.17e+09 7.27e+09 5.42e+09 1.70e+09 5.79e+10 ...
## $ Tourism and culture function expenditure (in IDR) : num [1:34] 5.87e+10 2.16e+10 1.22e+10 3.13e+11 3.30e+11 ...summary(data.indodapoer)## Provinces Name
## Length:34
## Class :character
## Mode :character
##
##
##
##
## Birth attended by Skilled Health worker (in % of total birth)
## Min. : 68.40
## 1st Qu.: 92.11
## Median : 96.11
## Mean : 93.48
## 3rd Qu.: 97.95
## Max. :100.00
##
## Capital expenditure (in IDR) Education function expenditure (in IDR)
## Min. :1.998e+11 Min. :5.113e+11
## 1st Qu.:6.169e+11 1st Qu.:1.337e+12
## Median :8.792e+11 Median :1.876e+12
## Mean :9.899e+11 Mean :3.339e+12
## 3rd Qu.:1.104e+12 3rd Qu.:3.333e+12
## Max. :3.173e+12 Max. :1.519e+13
##
## Environment function expenditure (in IDR)
## Min. :0.000e+00
## 1st Qu.:9.675e+09
## Median :1.619e+10
## Mean :1.289e+11
## 3rd Qu.:3.987e+10
## Max. :2.754e+12
##
## Goods and services expenditure (in IDR) Health function expenditure (in IDR)
## Min. :3.461e+11 Min. :1.140e+11
## 1st Qu.:7.520e+11 1st Qu.:3.795e+11
## Median :1.295e+12 Median :5.215e+11
## Mean :2.094e+12 Mean :1.015e+12
## 3rd Qu.:2.081e+12 3rd Qu.:9.592e+11
## Max. :1.678e+13 Max. :9.390e+12
##
## Household Access to Electricity: Total (in % of total household)
## Min. : 73.83
## 1st Qu.: 98.68
## Median : 99.26
## Mean : 97.79
## 3rd Qu.: 99.71
## Max. :100.00
##
## Household Access to safe Sanitation (in % of total Household)
## Min. :61.74
## 1st Qu.:76.27
## Median :82.33
## Mean :80.92
## 3rd Qu.:85.49
## Max. :93.55
##
## Household Access to Safe Water (in % of total household)
## Min. :37.22
## 1st Qu.:67.07
## Median :74.05
## Mean :73.20
## 3rd Qu.:80.47
## Max. :93.41
##
## Household per capita expenditure (in IDR)
## Min. : 794365
## 1st Qu.:1065363
## Median :1133381
## Mean :1252580
## 3rd Qu.:1381392
## Max. :2257984
##
## Literacy Rate for Population age 15 and over (in % of total population)
## Min. : 79.04
## 1st Qu.: 96.17
## Median :100.09
## Mean : 98.22
## 3rd Qu.:100.63
## Max. :102.12
##
## Monthly Per Capita Household Education Expenditure (in IDR)
## Min. : 25683
## 1st Qu.: 33884
## Median : 41576
## Mean : 49883
## 3rd Qu.: 55463
## Max. :121808
##
## Monthly Per Capita Household Health Expenditure (in IDR)
## Min. :13379
## 1st Qu.:20397
## Median :27078
## Mean :28673
## 3rd Qu.:35134
## Max. :57555
##
## Monthly Per Capita TOTAL Household Expenditure for The Poorest 20 percent (in IDR)
## Min. :305599
## 1st Qu.:397088
## Median :459221
## Mean :487203
## 3rd Qu.:557323
## Max. :797480
##
## Morbidity Rate (in %) Net Enrollment Ratio: Junior Secondary (in %)
## Min. :15.97 Min. :55.50
## 1st Qu.:25.10 1st Qu.:71.93
## Median :28.02 Median :78.48
## Mean :28.10 Mean :78.15
## 3rd Qu.:32.16 3rd Qu.:82.64
## Max. :44.00 Max. :97.76
##
## Net Enrollment Ratio: Primary (in %)
## Min. : 81.16
## 1st Qu.: 96.15
## Median : 98.79
## Mean : 98.05
## 3rd Qu.:100.53
## Max. :103.60
##
## Net Enrollment Ratio: Senior Secondary (in %) Others expenditure (in IDR)
## Min. :41.30 Min. :5.363e+11
## 1st Qu.:60.89 1st Qu.:1.217e+12
## Median :64.85 Median :2.329e+12
## Mean :64.14 Mean :4.343e+12
## 3rd Qu.:68.50 3rd Qu.:4.771e+12
## Max. :78.17 Max. :2.556e+13
##
## Personnel expenditure (in IDR)
## Min. :5.266e+11
## 1st Qu.:1.098e+12
## Median :1.541e+12
## Mean :2.444e+12
## 3rd Qu.:2.128e+12
## Max. :1.669e+13
##
## Public, law and order function expenditure (in IDR) Total Expenditure (in IDR)
## Min. :1.176e+10 Min. :1.805e+12
## 1st Qu.:3.150e+10 1st Qu.:4.219e+12
## Median :4.193e+10 Median :6.119e+12
## Mean :8.554e+10 Mean :9.871e+12
## 3rd Qu.:4.990e+10 3rd Qu.:9.846e+12
## Max. :1.491e+12 Max. :5.209e+13
##
## Total General Allocation Grant/DAU (in IDR)
## Min. :0.000e+00
## 1st Qu.:1.126e+12
## Median :1.436e+12
## Mean :1.567e+12
## 3rd Qu.:1.728e+12
## Max. :3.663e+12
##
## Total Natural Resources Revenue Sharing from Fishery (in IDR, realization value)
## Min. :0.000e+00
## 1st Qu.:0.000e+00
## Median :0.000e+00
## Mean :4.021e+07
## 3rd Qu.:0.000e+00
## Max. :1.327e+09
## NA's :1
## Total Natural Resources Revenue Sharing from Forestry (in IDR, realization value)
## Min. :0.000e+00
## 1st Qu.:3.494e+08
## Median :2.360e+09
## Mean :1.934e+10
## 3rd Qu.:1.062e+10
## Max. :1.590e+11
## NA's :1
## Total Natural Resources Revenue Sharing from Gas (in IDR, realization value)
## Min. :0.000e+00
## 1st Qu.:0.000e+00
## Median :0.000e+00
## Mean :1.028e+11
## 3rd Qu.:1.547e+10
## Max. :1.641e+12
## NA's :1
## Total Natural Resources Revenue Sharing from Geothermal Energy (in IDR, realization value)
## Min. :0.000e+00
## 1st Qu.:0.000e+00
## Median :0.000e+00
## Mean :1.126e+10
## 3rd Qu.:5.851e+08
## Max. :3.538e+11
## NA's :1
## Total Natural Resources Revenue Sharing from Mining (in IDR, realization value)
## Min. :0.000e+00
## 1st Qu.:4.316e+09
## Median :2.851e+10
## Mean :1.668e+11
## 3rd Qu.:8.306e+10
## Max. :2.340e+12
## NA's :1
## Total Natural Resources Revenue Sharing from Oil (in IDR, realization value)
## Min. :0.000e+00
## 1st Qu.:0.000e+00
## Median :9.535e+08
## Mean :7.621e+10
## 3rd Qu.:4.803e+10
## Max. :1.024e+12
## NA's :1
## Total Other Revenue (in IDR) Total Own Source Revenue/PAD (in IDR)
## Min. :1.207e+09 Min. :3.469e+11
## 1st Qu.:3.895e+10 1st Qu.:1.044e+12
## Median :8.219e+10 Median :1.846e+12
## Mean :7.709e+11 Mean :4.374e+12
## 3rd Qu.:1.219e+11 3rd Qu.:3.365e+12
## Max. :8.005e+12 Max. :3.741e+13
##
## Total Population (in number of people) Total Revenue (in IDR)
## Min. : 768505 Min. :1.863e+12
## 1st Qu.: 2313847 1st Qu.:3.771e+12
## Median : 4093134 Median :5.692e+12
## Mean : 7972540 Mean :9.801e+12
## 3rd Qu.: 8172977 3rd Qu.:9.941e+12
## Max. :49935858 Max. :5.589e+13
##
## Total Revenue Sharing Total Special Allocation Grant/DAK (in IDR)
## Min. :1.626e+10 Min. :3.740e+11
## 1st Qu.:1.480e+11 1st Qu.:7.230e+11
## Median :3.094e+11 Median :1.135e+12
## Mean :1.065e+12 Mean :2.024e+12
## 3rd Qu.:8.206e+11 3rd Qu.:2.251e+12
## Max. :1.365e+13 Max. :1.085e+13
##
## Total Tax Revenue Sharing from income tax (PPh) (in IDR, realization value)
## Min. :1.389e+10
## 1st Qu.:4.729e+10
## Median :1.034e+11
## Mean :6.109e+11
## 3rd Qu.:2.194e+11
## Max. :1.387e+13
##
## Total Tax Revenue Sharing from land and building tax (PBB) (in IDR, realization value)
## Min. :1.696e+09
## 1st Qu.:9.058e+09
## Median :2.940e+10
## Mean :7.019e+10
## 3rd Qu.:5.946e+10
## Max. :5.251e+11
##
## Tourism and culture function expenditure (in IDR)
## Min. :0.000e+00
## 1st Qu.:1.505e+10
## Median :2.425e+10
## Mean :4.724e+10
## 3rd Qu.:4.437e+10
## Max. :3.297e+11
## 1. Histogram
hist(data.indodapoer$`Household per capita expenditure (in IDR)`, breaks = 25, col = "coral",
xlab = "Household per capita expenditure (in IDR)",
main = "Household per capita expenditure Distribution (in IDR)")
2. Boxplot
boxplot(data.indodapoer$`Household per capita expenditure (in IDR)`, horizontal = TRUE, col = 'coral', xlab="Household per capita expenditure (in IDR)")
3. Density Plot (Naïve and Kernel)
3.1. Naïve Estimator
pengeluaranperkapita <- data.indodapoer$`Household per capita expenditure (in IDR)`
hist(pengeluaranperkapita, breaks= 25, col = "coral",
xlab= "Household per capita expenditure (in IDR)",
main = "",
freq = FALSE)
h = 100000
n = length(pengeluaranperkapita)
x <- seq(0, 3000000, by=10000)
fx <- NULL
for (i in 1:length(x)) {
fx[i] = sum(ifelse(abs(pengeluaranperkapita - x[i]) < h, 1, 0))/(2*h*n)
}
lines(x, fx, type="l", col="blue", lwd=2)
3.2. Kernel Estimator
dense <- density(data.indodapoer$`Household per capita expenditure (in IDR)`, bw=100000, kernel="epanechnikov")
hist(data.indodapoer$`Household per capita expenditure (in IDR)`, freq = FALSE, breaks = 100, col = "skyblue1", main = "", xlab = "Household per capita expenditure (in IDR)")
lines(dense, col="blue", lwd=2, main="", ylim=c(0, 0.000006))
4. Pie Chart
Eksplorasi Data Kategorik
mean(data.indodapoer$`Household per capita expenditure (in IDR)`)## [1] 1252579expenditure_above_mean <- ifelse(data.indodapoer$`Household per capita expenditure (in IDR)` > 1252579, "Yes","No")
table(expenditure_above_mean)## expenditure_above_mean
## No Yes
## 20 14frekuensi <- table(expenditure_above_mean)
prop.table(frekuensi)## expenditure_above_mean
## No Yes
## 0.5882353 0.4117647pie(frekuensi)
5. Bar Chart
barplot(frekuensi)
6. Scatter Plot
plot(data.indodapoer$`Household per capita expenditure (in IDR)`, data.indodapoer$`Household Access to Electricity: Total (in % of total household)`, ylab="Household per capita expenditure (in IDR)",
xlab = "Household Access to Electricity: Total (in % of total household)",
pch = 19, cex = 1.5,
col=ifelse(data.indodapoer$`Household per capita expenditure (in IDR)` >
1252579, "coral", "navyblue"))
7. Matrix Correlation
library(PerformanceAnalytics)## Warning: package 'PerformanceAnalytics' was built under R version 4.1.3## Loading required package: xts## Warning: package 'xts' was built under R version 4.1.3## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric##
## Attaching package: 'PerformanceAnalytics'## The following object is masked from 'package:graphics':
##
## legendchart.Correlation(data.indodapoer[,3:7], histogram = TRUE, pch= 19)
pairs(data.indodapoer[,3:7], pch=19, col="coral", cex=1.5)
8. Bubble Plot
library(tidyverse)## Warning: package 'tidyverse' was built under R version 4.1.3## -- Attaching packages --------------------------------------- tidyverse 1.3.2 --
## v ggplot2 3.3.6 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.9
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1## Warning: package 'ggplot2' was built under R version 4.1.3## Warning: package 'dplyr' was built under R version 4.1.3## Warning: package 'stringr' was built under R version 4.1.3## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::first() masks xts::first()
## x dplyr::lag() masks stats::lag()
## x dplyr::last() masks xts::last()library(hrbrthemes)## Warning: package 'hrbrthemes' was built under R version 4.1.3## NOTE: Either Arial Narrow or Roboto Condensed fonts are required to use these themes.
## Please use hrbrthemes::import_roboto_condensed() to install Roboto Condensed and
## if Arial Narrow is not on your system, please see https://bit.ly/arialnarrowlibrary(viridis)## Warning: package 'viridis' was built under R version 4.1.3## Loading required package: viridisLitelibrary(gridExtra)##
## Attaching package: 'gridExtra'
##
## The following object is masked from 'package:dplyr':
##
## combinelibrary(ggplot2)pengeluaran <- data.indodapoer$`Household per capita expenditure (in IDR)`data.indodapoer %>%
mutate(pengeluaran = pengeluaran/1000) %>%
arrange(desc(pengeluaran)) %>%
mutate(country = factor(`Provinces Name`, `Provinces Name`)) %>%
ggplot( aes(x=`Household Access to safe Sanitation (in % of total Household)`, y=`Household Access to Safe Water (in % of total household)`, size = data.indodapoer$`Household per capita expenditure (in IDR)`, color = `Provinces Name`)) +
geom_point(alpha=0.7) +
scale_size(range = c(1.4, 19), name="Pengeluaran") +
scale_color_viridis(discrete=TRUE, guide="none") +
theme_ipsum() +
theme(legend.position="bottom")## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family not
## found in Windows font database
## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family not
## found in Windows font database## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family not
## found in Windows font database## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## font family not found in Windows font database## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
9. Local Regression
library(readxl)
data.indodapoer.jabar <- read_xlsx("C:/Users/BANGSIS-1/Downloads/data_indodapoer_jabar.xlsx")
pengeluaran <- data.indodapoer.jabar$`Household per capita expenditure (in IDR)`data.indodapoer.jabar$index <- 1:nrow(data.indodapoer.jabar) # create index variable
loessMod10 <- loess(pengeluaran ~ index, data=data.indodapoer.jabar, span=0.10) # 10% smoothing span## Warning in simpleLoess(y, x, w, span, degree = degree, parametric =
## parametric, : span too small. fewer data values than degrees of freedom.## Warning in simpleLoess(y, x, w, span, degree = degree, parametric =
## parametric, : pseudoinverse used at 0.885## Warning in simpleLoess(y, x, w, span, degree = degree, parametric =
## parametric, : neighborhood radius 1.115## Warning in simpleLoess(y, x, w, span, degree = degree, parametric =
## parametric, : reciprocal condition number 0## Warning in simpleLoess(y, x, w, span, degree = degree, parametric =
## parametric, : There are other near singularities as well. 1.2432loessMod25 <- loess(pengeluaran ~ index, data=data.indodapoer.jabar, span=0.25) # 25% smoothing span
loessMod50 <- loess(pengeluaran ~ index, data=data.indodapoer.jabar, span=0.50) # 50% smoothing spansmoothed10 <- predict(loessMod10)
smoothed25 <- predict(loessMod25)
smoothed50 <- predict(loessMod50)plot(pengeluaran, x=data.indodapoer.jabar$`Series Name`, type="l", main="Loess Smoothing and Prediction", xlab="Year ", ylab="Household per capita expenditure (in IDR)")
lines(smoothed10, x=data.indodapoer.jabar$`Series Name`, col="red")
lines(smoothed25, x=data.indodapoer.jabar$`Series Name`, col="green")
lines(smoothed50, x=data.indodapoer.jabar$`Series Name`, col="blue")
legend('bottomright', legend=c('.1', '.25', '.5'),
col=c('red', 'green', 'blue'), pch=19, title='Smoothing Span')
Statistika dan Sains Data, IPB University, madania.agusta@apps.ipb.ac.id↩︎