title: “Analisis Regresi Data Panel (WDI 15 Negara)”
author: “Brithney Manopo”
date: “2026-11-19”
output:
html_document:
toc: true
toc_float: true
theme: cosmo
highlight: tango
pkgs <- c("readxl", "dplyr", "tidyr", "plm", "lmtest", "car", "tseries", "knitr")
for (p in pkgs) if (!requireNamespace(p, quietly = TRUE)) install.packages(p)
library(readxl); library(dplyr); library(tidyr); library(plm); library(lmtest); library(car); library(tseries); library(knitr)
file_path <- "C:/Users/a s u s/Downloads/Data WDI 15 Negara.xlsx"
if (!file.exists(file_path)) file_path <- file.choose()
tmp_xlsx <- tempfile(fileext = ".xlsx")
file.copy(file_path, tmp_xlsx, overwrite = TRUE)[1] TRUE
sheets_avail <- excel_sheets(tmp_xlsx)
target_sheet <- if ("Data" %in% sheets_avail) "Data" else sheets_avail[1]
raw_scan <- read_excel(tmp_xlsx, sheet = target_sheet, col_names = FALSE)
hdr_row <- which(apply(raw_scan, 1, function(r) grepl("Country|Series|Indicator|Tahun|Year|2000|2001|2010|2020", paste(na.omit(as.character(r)), collapse = " "), ignore.case = TRUE)))[1]
if (is.na(hdr_row)) hdr_row <- 1
raw_data <- read_excel(tmp_xlsx, sheet = target_sheet, skip = hdr_row - 1)
raw_data <- raw_data[, !grepl("^\\.\\.\\.[0-9]+$", names(raw_data)) | apply(raw_data, 2, function(c) any(!is.na(c)))]
cat("## 1. Tampilan Data Mentah & Struktur Awal\n\n")cat("- **Sheet Aktif:** `", target_sheet, "` | **Baris Awal:** ", nrow(raw_data), " | **Kolom Awal:** ", ncol(raw_data), "\n\n")Data | Baris
Awal: 65 | Kolom Awal: 27| Negara | Indikator | 2000 | 2001 | 2002 | 2003 | 2004 | 2005 | 2006 | 2007 | 2008 | 2009 | 2010 | 2011 | 2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 | 2019 | 2020 | 2021 | 2022 | 2023 | 2024 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Indonesia | Domestic credit to private sector (% of GDP) | .. | .. | .. | .. | .. | .. | .. | .. | .. | 27.6587 | 27.2530 | 30.0822 | 33.4342 | 36.0581 | 36.4235 | 39.1188 | 39.4024 | 38.7323 | 38.805449666563831 | 38.372693951660935 | 38.679539089145287 | 36.990827055625317 | 35.288432963268846 | 36.012951258869037 | 36.392406709514056 |
| Indonesia | Employment in services (% of total employment) (modeled ILO estimate) | 38.352998056901001 | 38.612238771833802 | 38.0265807831709 | 36.983998538692298 | 39.788658362821202 | 38.364835090415198 | 40.503824263964702 | 41.1092215565331 | 41.210525183387702 | 42.0006 | 42.9721 | 43.5903 | 43.7825 | 44.2425 | 44.4970 | 45.1011 | 46.6339 | 47.3558 | 48.168762274452902 | 49.135632900147499 | 49.056846345277101 | 49.2513693430476 | 48.847168554459202 | 49.2692149419358 | 49.753752667753602 |
| Indonesia | Mortality rate, under-5 (per 1,000 live births) | 51.4 | 49 | 46.7 | 44.6 | 48.6 | 40.700000000000003 | 38.9 | 37.200000000000003 | 35.6 | 34.1000 | 32.6000 | 31.2000 | 29.9000 | 28.6000 | 27.3000 | 26.1000 | 25.0000 | 23.8000 | 22.8 | 21.8 | 20.8 | 19.899999999999999 | 19.100000000000001 | 18.399999999999999 | 17.7 |
| Indonesia | Agricultural land (% of land area) | 23.764340067930071 | 24.202684500130225 | 24.522255167590849 | 24.788564057141365 | 24.837367824240395 | 24.939433369249524 | 25.520854915449593 | 26.049014683739554 | 26.204342006658788 | 26.5727 | 26.5683 | 27.0964 | 27.0920 | 27.3538 | 27.5091 | 27.6112 | 27.8731 | 27.7599 | 28.411834980098739 | 28.750329557250819 | 28.96499050076191 | 28.955848781541921 | 29.007381817864786 | 28.905172451284066 | 28.933374430838221 |
| Japan | Domestic credit to private sector (% of GDP) | 205.74957655097177 | 177.60004048631029 | 175.27391532686138 | 175.44585013008009 | 169.10028746763442 | 169.44439482144281 | 167.53837644246957 | 161.49252136222432 | 159.38351800694247 | 166.6337 | 158.5368 | 157.8460 | 157.9136 | 161.2470 | 160.8807 | 159.3376 | 160.5418 | 165.3776 | 164.29156633491669 | 172.1615037825398 | 189.48144870075211 | 187.9810756791513 | 186.54834684731048 | 186.42343835476348 | 187.97215818966743 |
| Japan | Employment in services (% of total employment) (modeled ILO estimate) | 64.1185656445506 | 65.122478810294893 | 66.219783125694505 | 66.302120093188705 | 67.238696018052195 | 67.841607204856103 | 67.887146650735801 | 68.121489386786294 | 68.652490446501005 | 69.3381 | 70.0547 | 70.4131 | 70.6286 | 70.9248 | 71.0613 | 71.3122 | 71.7448 | 71.8208 | 72.038844415274696 | 72.398807561451903 | 72.811017042505199 | 73.136394730663497 | 73.282831534033704 | 73.286015838644204 | 73.772706405057903 |
| Japan | Mortality rate, under-5 (per 1,000 live births) | 4.5 | 4.3 | 4.0999999999999996 | 4 | 3.9 | 3.7 | 3.6 | 3.5 | 3.4 | 3.4000 | 3.3000 | 3.3000 | 3.1000 | 3.0000 | 2.9000 | 2.8000 | 2.7000 | 2.6000 | 2.5 | 2.5 | 2.4 | 2.4 | 2.4 | 2.4 | 2.4 |
| Japan | Agricultural land (% of land area) | 14.425240054869684 | 14.301783264746229 | 14.19753086419753 | 14.101508916323732 | 14.01920438957476 | 13.936899862825788 | 13.863923182441701 | 13.790946502057613 | 13.715226337448561 | 13.6477 | 13.5885 | 13.4952 | 13.4568 | 13.4211 | 13.3608 | 13.2949 | 13.2044 | 13.1084 | 13.020576131687243 | 12.935528120713306 | 12.844993141289438 | 12.781893004115227 | 12.716049382716049 | 12.63923182441701 | 12.570644718792867 |
nms <- names(raw_data)
yr_wdi <- grep("\\[YR[0-9]{4}\\]$", nms, value = TRUE)
yr_num <- nms[suppressWarnings(!is.na(as.numeric(nms))) & suppressWarnings(as.numeric(nms)) >= 1960 & suppressWarnings(as.numeric(nms)) <= 2030]
if (length(yr_wdi) > 0 && any(c("Series Code", "Series Name", "Indicator Code", "Indicator Name") %in% nms)) {
ind_col <- intersect(c("Series Code", "Series Name", "Indicator Code", "Indicator Name"), nms)[1]
cnt_col <- if ("Country Name" %in% nms) "Country Name" else nms[1]
df_panel <- raw_data %>%
pivot_longer(cols = all_of(yr_wdi), names_to = "thn_raw", values_to = "val_raw", values_transform = list(val_raw = as.character)) %>%
mutate(negara = trimws(as.character(.data[[cnt_col]])), indikator = trimws(as.character(.data[[ind_col]])), tahun = suppressWarnings(as.integer(sub(".*\\[YR([0-9]{4})\\]$", "\\1", thn_raw))), nilai = suppressWarnings(as.numeric(ifelse(trimws(val_raw) %in% c("", "..", "NA", "-"), NA, trimws(val_raw))))) %>%
filter(!is.na(negara), negara != "", !grepl("Data from database|Last Updated|Source:", negara, ignore.case = TRUE), !is.na(indikator), indikator != "", !is.na(tahun)) %>%
group_by(negara, tahun, indikator) %>% summarise(nilai = if (all(is.na(nilai))) NA_real_ else mean(nilai, na.rm = TRUE), .groups = "drop") %>%
pivot_wider(names_from = indikator, values_from = nilai)
} else if (length(yr_num) > 0) {
cnt_col <- nms[1]; ind_col <- if (length(nms) > 2 && !nms[2] %in% yr_num) nms[2] else NULL
if (!is.null(ind_col)) {
df_panel <- raw_data %>%
pivot_longer(cols = all_of(yr_num), names_to = "tahun", values_to = "val_raw", values_transform = list(val_raw = as.character)) %>%
mutate(negara = trimws(as.character(.data[[cnt_col]])), indikator = trimws(as.character(.data[[ind_col]])), tahun = suppressWarnings(as.integer(tahun)), nilai = suppressWarnings(as.numeric(ifelse(trimws(val_raw) %in% c("", "..", "NA", "-"), NA, trimws(val_raw))))) %>%
filter(!is.na(negara), negara != "", !grepl("Data from database|Last Updated|Source:", negara, ignore.case = TRUE), !is.na(indikator), indikator != "", !is.na(tahun)) %>%
group_by(negara, tahun, indikator) %>% summarise(nilai = if (all(is.na(nilai))) NA_real_ else mean(nilai, na.rm = TRUE), .groups = "drop") %>%
pivot_wider(names_from = indikator, values_from = nilai)
} else {
df_panel <- raw_data %>% pivot_longer(cols = all_of(yr_num), names_to = "tahun", values_to = "val_raw", values_transform = list(val_raw = as.character)) %>% mutate(negara = trimws(as.character(.data[[cnt_col]])), tahun = suppressWarnings(as.integer(tahun)), nilai = suppressWarnings(as.numeric(ifelse(trimws(val_raw) %in% c("", "..", "NA", "-"), NA, trimws(val_raw))))) %>% filter(!is.na(negara), negara != "", !is.na(tahun))
}
} else {
df_panel <- raw_data; names(df_panel)[1:2] <- c("negara", "tahun")
df_panel <- df_panel %>% fill(negara, .direction = "down") %>% mutate(negara = trimws(as.character(negara)), tahun = suppressWarnings(as.integer(as.character(tahun))), across(-c(negara, tahun), ~ suppressWarnings(as.numeric(as.character(.)))))
}
names(df_panel) <- make.names(names(df_panel), unique = TRUE)
df_panel <- df_panel %>% fill(negara, .direction = "down") %>% filter(!is.na(negara), negara != "", !is.na(tahun))
num_cols <- names(df_panel)[sapply(df_panel, is.numeric) & names(df_panel) != "tahun"]
vars_uji <- num_cols[1:min(4, length(num_cols))]
df_clean <- df_panel %>% select(negara, tahun, all_of(vars_uji)) %>% filter(if_all(all_of(vars_uji), ~ is.finite(.x))) %>% mutate(negara = as.factor(negara))
cat("\n\n## 2. Data Panel Bersih & Statistik Deskriptif\n\n")cat("- **Variabel Analisis:** `", paste(vars_uji, collapse = "`, `"), "` | **Observasi Valid:** ", nrow(df_clean), " | **Negara:** ", length(unique(df_clean$negara)), " | **Periode:** ", min(df_clean$tahun), "-", max(df_clean$tahun), "\n\n")Agricultural.land....of.land.area.,
Domestic.credit.to.private.sector....of.GDP.,
Employment.in.services....of.total.employment...modeled.ILO.estimate.,
Mortality.rate..under.5..per.1.000.live.births. |
Observasi Valid: 336 | Negara: 15 |
Periode: 2000 - 2024print(kable(head(df_clean, 10), digits = 4, caption = "Cuplikan 10 Baris Data Panel Siap Analisis"))| negara | tahun | Agricultural.land….of.land.area. | Domestic.credit.to.private.sector….of.GDP. | Employment.in.services….of.total.employment…modeled.ILO.estimate. | Mortality.rate..under.5..per.1.000.live.births. |
|---|---|---|---|---|---|
| Brunei Darussalam | 2006 | 2.2524 | 31.7046 | 79.0835 | 9.5 |
| Brunei Darussalam | 2007 | 2.2713 | 34.2004 | 79.6101 | 9.6 |
| Brunei Darussalam | 2008 | 2.5180 | 31.7685 | 79.7217 | 9.6 |
| Brunei Darussalam | 2009 | 2.5180 | 40.1018 | 80.1785 | 9.7 |
| Brunei Darussalam | 2010 | 2.5180 | 36.9083 | 80.2978 | 9.9 |
| Brunei Darussalam | 2011 | 2.5180 | 28.1209 | 80.1145 | 10.0 |
| Brunei Darussalam | 2012 | 2.6812 | 27.9921 | 80.1688 | 10.2 |
| Brunei Darussalam | 2013 | 2.6812 | 31.1924 | 80.4935 | 10.4 |
| Brunei Darussalam | 2014 | 2.6812 | 33.2080 | 80.7192 | 10.6 |
| Brunei Darussalam | 2015 | 2.6812 | 41.4363 | 81.3408 | 10.7 |
desk_tbl <- lapply(vars_uji, function(v) {
x <- df_clean[[v]]
data.frame(Variabel = v, N = length(x), Rata_Rata = mean(x), Simpangan_Baku = sd(x), Minimum = min(x), Median = median(x), Maksimum = max(x))
}) %>% bind_rows()
print(kable(desk_tbl, digits = 4, row.names = FALSE, caption = "Ringkasan Statistik Deskriptif"))| Variabel | N | Rata_Rata | Simpangan_Baku | Minimum | Median | Maksimum |
|---|---|---|---|---|---|---|
| Agricultural.land….of.land.area. | 336 | 32.6147 | 19.9336 | 0.9201 | 30.9652 | 80.8488 |
| Domestic.credit.to.private.sector….of.GDP. | 336 | 78.3224 | 54.1151 | 3.1211 | 54.9327 | 205.7496 |
| Employment.in.services….of.total.employment…modeled.ILO.estimate. | 336 | 50.0159 | 18.3955 | 17.9876 | 47.3276 | 85.0623 |
| Mortality.rate..under.5..per.1.000.live.births. | 336 | 27.1143 | 26.6180 | 2.4000 | 18.4500 | 107.9000 |
has_cips <- exists("cipstest", where = asNamespace("plm"), mode = "function")
uji_awal <- lapply(vars_uji, function(v) {
s0 <- pdata[[v]]; s1 <- tryCatch(diff(s0), error = function(e) NULL)
c0 <- if (has_cips) tryCatch(as.numeric(plm::cipstest(s0, lags = 1, type = "drift")$p.value), error = function(e) NA_real_) else NA_real_
c1 <- if (has_cips && !is.null(s1)) tryCatch(as.numeric(plm::cipstest(s1, lags = 1, type = "drift")$p.value), error = function(e) NA_real_) else NA_real_
ip0 <- tryCatch(as.numeric(purtest(s0, test = "ips", exo = "intercept", lags = 1)$statistic$p.value), error = function(e) NA_real_)
cd0 <- tryCatch(pcdtest(s0, test = "cd"), error = function(e) NULL)
data.frame(Variabel = v, CIPS_Level_p = c0, CIPS_Diff1_p = c1, IPS_Level_p = ip0, Pesaran_CD_Stat = if (!is.null(cd0)) as.numeric(cd0$statistic) else NA_real_, Pesaran_CD_p = if (!is.null(cd0)) as.numeric(cd0$p.value) else NA_real_, Stasioneritas = ifelse(!is.na(c0) & c0 <= 0.05, "Stasioner I(0)", ifelse(!is.na(c1) & c1 <= 0.05, "Stasioner I(1)", "Cek Lag")), Cross_Section = if (!is.null(cd0)) ifelse(cd0$p.value <= 0.05, "Ada Dependensi (p <= 0.05)", "Independen (p > 0.05)") else "N/A")
}) %>% bind_rows()
print(kable(uji_awal, digits = 4, row.names = FALSE, caption = "Hasil Uji Stasioneritas CIPS/IPS dan Cross-Sectional Independence"))| Variabel | CIPS_Level_p | CIPS_Diff1_p | IPS_Level_p | Pesaran_CD_Stat | Pesaran_CD_p | Stasioneritas | Cross_Section |
|---|---|---|---|---|---|---|---|
| Agricultural.land….of.land.area. | 0.1000 | 0.0464 | 0.3200 | -1.7561 | 0.0791 | Stasioner I(1) | Independen (p > 0.05) |
| Domestic.credit.to.private.sector….of.GDP. | 0.0837 | 0.0486 | 0.6002 | 14.3202 | 0.0000 | Stasioner I(1) | Ada Dependensi (p <= 0.05) |
| Employment.in.services….of.total.employment…modeled.ILO.estimate. | 0.1000 | 0.0100 | 0.9294 | 31.5902 | 0.0000 | Stasioner I(1) | Ada Dependensi (p <= 0.05) |
| Mortality.rate..under.5..per.1.000.live.births. | 0.0100 | 0.0319 | 0.0000 | 32.4830 | 0.0000 | Stasioner I(0) | Ada Dependensi (p <= 0.05) |
if (length(vars_uji) >= 2) {
f_panel <- as.formula(paste(vars_uji[1], "~", paste(vars_uji[-1], collapse = " + ")))
cat("\n\n## 4. Uji Heterogenitas\n\n```\n")
print(tryCatch(pooltest(f_panel, data = pdata, model = "within"), error = function(e) e$message))
print(tryCatch(summary(pvcm(f_panel, data = pdata, model = "within")), error = function(e) e$message))
cat("```\n\n## 5. Pemilihan Model & Estimasi\n\n```\n")
cem <- plm(f_panel, data = pdata, model = "pooling"); fem <- plm(f_panel, data = pdata, model = "within"); rem <- tryCatch(plm(f_panel, data = pdata, model = "random"), error = function(e) NULL)
print(pFtest(fem, cem)); if (!is.null(rem)) print(tryCatch(phtest(fem, rem), error = function(e) e$message)); print(tryCatch(plmtest(cem, type = "bp"), error = function(e) e$message)); print(summary(fem))
cat("```\n\n### 6. Uji Asumsi Model\n\n```\n")
print(pbgtest(fem)); print(bptest(lm(update(f_panel, . ~ . + factor(negara)), data = df_clean))); print(tryCatch(pcdtest(fem, test = "cd"), error = function(e) e$message))
if (length(vars_uji) > 2) print(vif(lm(f_panel, data = df_clean)))
res_e <- as.numeric(residuals(fem)); print(shapiro.test(res_e)); print(jarque.bera.test(res_e))
cat("```\n\n### 7. Estimasi Driscoll-Kraay Robust Standard Errors\n\n```\n")
print(coeftest(fem, vcov = function(x) vcovSCC(x, type = "HC0", cluster = "group")))
cat("```\n\n")
}
F statistic
data: f_panel
F = 62.539, df1 = 42, df2 = 276, p-value < 2.2e-16
alternative hypothesis: unstability
Oneway (individual) effect No-pooling model
Call:
pvcm(formula = f_panel, data = pdata, model = "within")
Unbalanced Panel: n = 15, T = 16-25, N = 336
Residuals:
Min. 1st Qu. Median 3rd Qu. Max.
-1.864920 -0.147546 -0.005048 0.128867 2.124958
Coefficients:
(Intercept) Domestic.credit.to.private.sector....of.GDP.
Min. :-8.404 Min. :-0.1342785
1st Qu.:11.170 1st Qu.:-0.0103240
Median :30.699 Median :-0.0004938
Mean :30.889 Mean :-0.0033566
3rd Qu.:49.511 3rd Qu.: 0.0162772
Max. :82.343 Max. : 0.0772170
Employment.in.services....of.total.employment...modeled.ILO.estimate.
Min. :-0.27432
1st Qu.:-0.03333
Median : 0.03819
Mean : 0.09028
3rd Qu.: 0.16869
Max. : 0.60208
Mortality.rate..under.5..per.1.000.live.births.
Min. :-1.423628
1st Qu.:-0.064806
Median : 0.001513
Mean : 0.031102
3rd Qu.: 0.331170
Max. : 1.282442
Total Sum of Squares: 2e+06
Residual Sum of Squares: 62.046
Multiple R-Squared: 0.99997
F test for individual effects
data: f_panel
F = 3601.9, df1 = 14, df2 = 318, p-value < 2.2e-16
alternative hypothesis: significant effects
Hausman Test
data: f_panel
chisq = 6.7266, df = 3, p-value = 0.08114
alternative hypothesis: one model is inconsistent
Lagrange Multiplier Test - (Breusch-Pagan)
data: f_panel
chisq = 2553.1, df = 1, p-value < 2.2e-16
alternative hypothesis: significant effects
Oneway (individual) effect Within Model
Call:
plm(formula = f_panel, data = pdata, model = "within")
Unbalanced Panel: n = 15, T = 16-25, N = 336
Residuals:
Min. 1st Qu. Median 3rd Qu. Max.
-5.0621 -0.5977 0.0233 0.6740 4.1554
Coefficients:
Estimate
Domestic.credit.to.private.sector....of.GDP. 0.0122373
Employment.in.services....of.total.employment...modeled.ILO.estimate. 0.0404381
Mortality.rate..under.5..per.1.000.live.births. -0.0198719
Std. Error
Domestic.credit.to.private.sector....of.GDP. 0.0060062
Employment.in.services....of.total.employment...modeled.ILO.estimate. 0.0339089
Mortality.rate..under.5..per.1.000.live.births. 0.0090822
t-value
Domestic.credit.to.private.sector....of.GDP. 2.0374
Employment.in.services....of.total.employment...modeled.ILO.estimate. 1.1926
Mortality.rate..under.5..per.1.000.live.births. -2.1880
Pr(>|t|)
Domestic.credit.to.private.sector....of.GDP. 0.04243
Employment.in.services....of.total.employment...modeled.ILO.estimate. 0.23393
Mortality.rate..under.5..per.1.000.live.births. 0.02940
Domestic.credit.to.private.sector....of.GDP. *
Employment.in.services....of.total.employment...modeled.ILO.estimate.
Mortality.rate..under.5..per.1.000.live.births. *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Total Sum of Squares: 740.78
Residual Sum of Squares: 652.52
R-Squared: 0.11914
Adj. R-Squared: 0.07205
F-statistic: 14.337 on 3 and 318 DF, p-value: 8.7518e-09
Breusch-Godfrey/Wooldridge test for serial correlation in panel models
data: f_panel
chisq = 274.98, df = 16, p-value < 2.2e-16
alternative hypothesis: serial correlation in idiosyncratic errors
studentized Breusch-Pagan test
data: lm(update(f_panel, . ~ . + factor(negara)), data = df_clean)
BP = 182.58, df = 17, p-value < 2.2e-16
Pesaran CD test for cross-sectional dependence in panels
data: Agricultural.land....of.land.area. ~ Domestic.credit.to.private.sector....of.GDP. + Employment.in.services....of.total.employment...modeled.ILO.estimate. + Mortality.rate..under.5..per.1.000.live.births.
z = -2.3107, p-value = 0.02085
alternative hypothesis: cross-sectional dependence
Domestic.credit.to.private.sector....of.GDP.
2.027921
Employment.in.services....of.total.employment...modeled.ILO.estimate.
2.063303
Mortality.rate..under.5..per.1.000.live.births.
3.412500
Shapiro-Wilk normality test
data: res_e
W = 0.96254, p-value = 1.378e-07
Jarque Bera Test
data: res_e
X-squared = 25.489, df = 2, p-value = 2.918e-06
t test of coefficients:
Estimate
Domestic.credit.to.private.sector....of.GDP. 0.012237
Employment.in.services....of.total.employment...modeled.ILO.estimate. 0.040438
Mortality.rate..under.5..per.1.000.live.births. -0.019872
Std. Error
Domestic.credit.to.private.sector....of.GDP. 0.019353
Employment.in.services....of.total.employment...modeled.ILO.estimate. 0.136378
Mortality.rate..under.5..per.1.000.live.births. 0.022785
t value
Domestic.credit.to.private.sector....of.GDP. 0.6323
Employment.in.services....of.total.employment...modeled.ILO.estimate. 0.2965
Mortality.rate..under.5..per.1.000.live.births. -0.8722
Pr(>|t|)
Domestic.credit.to.private.sector....of.GDP. 0.5276
Employment.in.services....of.total.employment...modeled.ILO.estimate. 0.7670
Mortality.rate..under.5..per.1.000.live.births. 0.3838