1 Exploración de la dependiente
linkLL='https://docs.google.com/spreadsheets/d/e/2PACX-1vQUWlFgjXdo-Tptb1fhFyYjDV8bS-ZC-RBV_vNPdC80ORIFBz7zt4c1nI6bizAeKogdZ9e2y22uu-1n/pub?gid=962341748&single=true&output=csv'
Depart=read.csv(linkLL, stringsAsFactors = F)
# que tenemos
str(Depart)## 'data.frame': 83 obs. of 3 variables:
## $ Analfabetismo: num 1.5 5.3 4.4 3.9 3.7 5.7 3.5 9.8 2.8 11.1 ...
## $ Agua : num 3.1 16.1 5.1 42.8 15.7 7.9 18 6.3 12.5 11.6 ...
## $ Energia : num 0.7 6.3 1.6 6.6 4.3 3.3 4 6.7 5 10 ...1.1 Exploración gráfica
library(ggplot2)
base1=ggplot(Depart,aes(x=Analfabetismo))
histNum= base1 + geom_histogram(bins=7)
histNum 
Atipicos
base2=ggplot(Depart,aes(y=Analfabetismo))
box=base2 + geom_boxplot() + coord_flip()
box
1.2 Exploración con estadígrafos
summary(Depart$Analfabetismo)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.50 6.40 11.70 12.56 17.20 30.30Podriamos graficarlos en el boxplot:
estadigrafos=round(as.vector(summary(Depart$Analfabetismo)),2)
box + scale_y_continuous(breaks = estadigrafos) 
library(DescTools)
Skew(Depart$Analfabetismo,conf.level = 0.05)## skew lwr.ci upr.ci
## 0.4418950 0.4498141 0.4725494IQR(Depart$Analfabetismo)## [1] 10.8# cuartil tres
q3=as.numeric(summary(Depart$Analfabetismo)[5])
# calculando umbral (distancia del q3)
umbral= q3+1.5*IQR(Depart$Analfabetismo)
umbral## [1] 33.4Depart[Depart$Analfabetismo>umbral,]## [1] Analfabetismo Agua Energia
## <0 rows> (or 0-length row.names)Gini(Depart$Analfabetismo,conf.level=0.95)## gini lwr.ci upr.ci
## 0.3194691 0.2846361 0.3642236base1 + gglorenz::stat_lorenz(color='red') +
geom_abline(linetype = "dashed") + coord_fixed() +
labs(x = "% Distritos",
y = "% Tasa de analfabetismo",
title = "Relación Distrito / Tasa de analfabetismo",
caption = "Fuente: INEI")## Registered S3 methods overwritten by 'ineq':
## method from
## plot.Lc DescTools
## lines.Lc DescTools
2. Exploracion bivariada
Test de normalidad
library(dlookr)## Loading required package: mice##
## Attaching package: 'mice'## The following object is masked from 'package:stats':
##
## filter## The following objects are masked from 'package:base':
##
## cbind, rbind## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo## Warning in fun(libname, pkgname): couldn't connect to display ":0"##
## Attaching package: 'dlookr'## The following object is masked from 'package:base':
##
## transformnormality(Depart[,c(1,2,3)])## # A tibble: 3 x 4
## vars statistic p_value sample
## <chr> <dbl> <dbl> <dbl>
## 1 Analfabetismo 0.959 0.0100 83
## 2 Agua 0.888 0.00000267 83
## 3 Energia 0.879 0.00000118 83HN 1
library(ggpubr)
HN1=ggscatter(Depart,
x = "Agua", y = "Analfabetismo",
cor.coef = TRUE,
cor.method = "spearman") # spearman?
HN1
HN2
library(ggpubr)
HN2=ggscatter(Depart,
x = "Energia", y = "Analfabetismo",
cor.coef = TRUE,
cor.method = "spearman") # spearman?
HN2
3. Regresión
3.1 Analisis de la dependiente
3.1.1 Verificar normalidad
shapiro.test(Depart$Analfabetismo)##
## Shapiro-Wilk normality test
##
## data: Depart$Analfabetismo
## W = 0.95925, p-value = 0.010043.1.2 Verificar asimetria y si hay atipicos
Skew(Depart$Analfabetismo)## [1] 0.441895Histograma
base=ggplot(data=Depart, aes(x=Analfabetismo))
base+geom_histogram(bins=20) 
Diagrama de cajas
base=ggplot(data=Depart, aes(y=Analfabetismo))
base+geom_boxplot() + coord_flip()
3.2 Analisis bivariado
3.2.1 Hipotesis 1
HS1=formula(~ Analfabetismo + Agua)
cor.test(HS1,data=Depart,method = "spearm",exact=F)##
## Spearman's rank correlation rho
##
## data: Analfabetismo and Agua
## S = 43400, p-value = 1.03e-07
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## 0.5445147ggscatter(Depart,
x = "Agua", y = "Analfabetismo",
cor.coef = TRUE,
cor.method = "spearman",
add = "reg.line",
add.params = list(color = "blue", fill = "lightgray"),
conf.int = TRUE) ## `geom_smooth()` using formula 'y ~ x'
3.2.1 Hipotesis 2
HS2=formula(~ Analfabetismo + Energia)
cor.test(HS2,data=Depart,method = "spearm",exact=F)##
## Spearman's rank correlation rho
##
## data: Analfabetismo and Energia
## S = 26014, p-value = 7.183e-15
## alternative hypothesis: true rho is not equal to 0
## sample estimates:
## rho
## 0.7269798ggscatter(Depart,
x = "Energia", y = "Analfabetismo",
cor.coef = TRUE,
cor.method = "spearman",
add = "reg.line",
add.params = list(color = "blue", fill = "lightgray"),
conf.int = TRUE) ## `geom_smooth()` using formula 'y ~ x'
3.2 Análisis regresión
names(Depart)## [1] "Analfabetismo" "Agua" "Energia"DepartReg=lm(Analfabetismo~.,data=Depart)
summary(DepartReg)##
## Call:
## lm(formula = Analfabetismo ~ ., data = Depart)
##
## Residuals:
## Min 1Q Median 3Q Max
## -13.9272 -3.3010 -0.9079 3.7909 12.1031
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.79245 1.05765 5.477 4.86e-07 ***
## Agua 0.05972 0.02067 2.890 0.00496 **
## Energia 0.14035 0.02632 5.332 8.79e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 5.24 on 80 degrees of freedom
## Multiple R-squared: 0.4557, Adjusted R-squared: 0.4421
## F-statistic: 33.49 on 2 and 80 DF, p-value: 2.717e-11