library(htmltab)
LINK6="https://es.wikipedia.org/wiki/%C3%8Dndice_global_de_felicidad"
GMT='//*[@id="mw-content-text"]/div/table'
feliz=htmltab(doc= LINK6,
which = GMT)names(feliz)## [1] "№"
## [2] "País"
## [3] "Puntuación"
## [4] "PIB per cápita"
## [5] "Apoyo social"
## [6] "Esperanza de años de vida saludable"
## [7] "Libertad para tomar decisiones vitales"
## [8] "Generosidad"
## [9] "Percepción de la corrupción"str(feliz)## 'data.frame': 156 obs. of 9 variables:
## $ № : chr "1" "2" "3" "4" ...
## $ País : chr "Finlandia" "Colombia" "Noruega" "Dinamarca" ...
## $ Puntuación : chr "7.633" "7.594" "7.560" "7.555" ...
## $ PIB per cápita : chr "1.305" "1.456" "1.372" "1.351" ...
## $ Apoyo social : chr "1.592" "1.582" "1.595" "1.590" ...
## $ Esperanza de años de vida saludable : chr "0.874" "0.873" "0.870" "0.868" ...
## $ Libertad para tomar decisiones vitales: chr "0.681" "0.686" "0.685" "0.683" ...
## $ Generosidad : chr "0.192" "0.286" "0.285" "0.284" ...
## $ Percepción de la corrupción : chr "0.393" "0.130" "0.410" "0.408" ...library(stringr)
names(feliz)=str_split(names(feliz)," ",simplify = T)[,1]feliz[,c(3:9)]=lapply(feliz[,c(3:9)],as.numeric)str(feliz)## 'data.frame': 156 obs. of 9 variables:
## $ № : chr "1" "2" "3" "4" ...
## $ País : chr "Finlandia" "Colombia" "Noruega" "Dinamarca" ...
## $ Puntuación : num 7.63 7.59 7.56 7.55 7.5 ...
## $ PIB : num 1.3 1.46 1.37 1.35 1.34 ...
## $ Apoyo : num 1.59 1.58 1.59 1.59 1.64 ...
## $ Esperanza : num 0.874 0.873 0.87 0.868 0.914 0.927 0.878 0.896 0.876 0.913 ...
## $ Libertad : num 0.681 0.686 0.685 0.683 0.677 0.66 0.638 0.653 0.669 0.659 ...
## $ Generosidad: num 0.192 0.286 0.285 0.284 0.353 0.256 0.333 0.321 0.365 0.285 ...
## $ Percepción : num 0.393 0.13 0.41 0.408 0.138 0.357 0.295 0.291 0.389 0.383 ...pregunta uno, la variable dependiente es (esperanza de años de vida saludable) veamos la normalidad de todas las variables:
library(dlookr)## Loading required package: mice## Loading required package: lattice##
## Attaching package: 'mice'## The following objects are masked from 'package:base':
##
## cbind, rbind## Registered S3 method overwritten by 'xts':
## method from
## as.zoo.xts zoo## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo## Registered S3 methods overwritten by 'car':
## method from
## influence.merMod lme4
## cooks.distance.influence.merMod lme4
## dfbeta.influence.merMod lme4
## dfbetas.influence.merMod lme4## Warning in fun(libname, pkgname): couldn't connect to display ":0"##
## Attaching package: 'dlookr'## The following object is masked from 'package:base':
##
## transformnormality(feliz)## Warning: `cols` is now required.
## Please use `cols = c(statistic)`## # A tibble: 7 x 4
## vars statistic p_value sample
## <chr> <dbl> <dbl> <dbl>
## 1 Puntuación 0.984 6.48e- 2 156
## 2 PIB 0.977 1.18e- 2 156
## 3 Apoyo 0.917 8.71e- 8 156
## 4 Esperanza 0.954 5.15e- 5 156
## 5 Libertad 0.946 1.13e- 5 156
## 6 Generosidad 0.960 1.79e- 4 156
## 7 Percepción 0.814 8.49e-13 156son anormales veamos la regresion
todas=lm(Esperanza~PIB+Apoyo+Libertad+Generosidad+Percepción,data=feliz)
summary(todas)##
## Call:
## lm(formula = Esperanza ~ PIB + Apoyo + Libertad + Generosidad +
## Percepción, data = feliz)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.44391 -0.06484 0.01431 0.07939 0.24825
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.003605 0.047854 -0.075 0.94004
## PIB 0.445871 0.036908 12.081 < 2e-16 ***
## Apoyo 0.139466 0.048666 2.866 0.00476 **
## Libertad 0.046434 0.078767 0.590 0.55641
## Generosidad -0.002610 0.116482 -0.022 0.98216
## Percepción 0.122647 0.128416 0.955 0.34108
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1295 on 150 degrees of freedom
## Multiple R-squared: 0.7373, Adjusted R-squared: 0.7285
## F-statistic: 84.18 on 5 and 150 DF, p-value: < 2.2e-16pbi y generoosidad: amabas son anormales
num1=formula(~PIB + Generosidad)
cor.test(num1,data=feliz,method = "pearson",exact=F)##
## Pearson's product-moment correlation
##
## data: PIB and Generosidad
## t = -0.060844, df = 154, p-value = 0.9516
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## -0.1619189 0.1523552
## sample estimates:
## cor
## -0.004902909ahora en un grafico:
library(ggpubr)## Loading required package: ggplot2## Loading required package: magrittrs2=ggscatter(feliz,
x = "Generosidad", y = "PIB",
cor.coef = TRUE,
cor.method = "spearman")
s2
la correlacion es minima ## entre años de vida saludable y percepcion de corrupcion.
num2=formula(~Esperanza + Percepción)
cor.test(num2,data=feliz,method = "pearson",exact=F)##
## Pearson's product-moment correlation
##
## data: Esperanza and Percepción
## t = 4.0953, df = 154, p-value = 6.791e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1643339 0.4484393
## sample estimates:
## cor
## 0.313382s3=ggscatter(feliz,
x = "Percepción", y = "Esperanza",
cor.coef = TRUE,
cor.method = "spearman")
s3
## tomando a perdepcino como dependiente:
todas=lm(Percepción~PIB+Apoyo+Libertad+Generosidad+Esperanza,data=feliz)
summary(todas)##
## Call:
## lm(formula = Percepción ~ PIB + Apoyo + Libertad + Generosidad +
## Esperanza, data = feliz)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.18413 -0.05413 -0.01276 0.04097 0.31134
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.04356 0.03013 -1.446 0.150266
## PIB 0.04141 0.03269 1.267 0.207190
## Apoyo -0.03841 0.03153 -1.218 0.225052
## Libertad 0.19913 0.04727 4.213 4.34e-05 ***
## Generosidad 0.25261 0.07090 3.563 0.000492 ***
## Esperanza 0.04928 0.05160 0.955 0.341075
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.08212 on 150 degrees of freedom
## Multiple R-squared: 0.3098, Adjusted R-squared: 0.2868
## F-statistic: 13.47 on 5 and 150 DF, p-value: 7.529e-11segunda parte
link="https://docs.google.com/spreadsheets/d/e/2PACX-1vTgL5kS-g3Q5TuAhkIAsnnz-nqPg-WREgkWA9y2sWPRSUPKIHWknh9hJY7UcXRFWA/pub?output=csv"
IDE=read.csv(link, stringsAsFactors = F)str(IDE)## 'data.frame': 195 obs. of 13 variables:
## $ regionUbigeo : int 10000 10000 10000 10000 10000 10000 10000 20000 20000 20000 ...
## $ provinciaUbigeo: int 10100 10200 10300 10400 10500 10600 10700 20100 20200 20300 ...
## $ PROVINCIA : chr "CHACHAPOYAS" "BAGUA" "BONGARA" "CONDORCANQUI" ...
## $ IDE : num 0.774 0.662 0.632 0.46 0.605 ...
## $ identidad : num 98.6 94.6 97.5 86.2 96.2 ...
## $ salud : num 25.45 14.61 9.01 8.56 12.42 ...
## $ educacion : num 91.5 79.8 76.4 52.2 74.7 ...
## $ saneamiento : num 70.3 64.5 54.8 37.7 43.3 ...
## $ electrificacion: num 84 67.9 72.2 39.5 67.4 ...
## $ poblacion : int 54783 77438 32317 51802 52185 30236 118747 161003 7974 16879 ...
## $ costa : chr "NO" "NO" "NO" "NO" ...
## $ capital : chr "SI" "NO" "NO" "NO" ...
## $ tamano : chr "Pequena" "Pequena" "Muy pequena" "Pequena" ...names(IDE)=str_split(names(IDE)," ",simplify = T)[,1]names(IDE)## [1] "regionUbigeo" "provinciaUbigeo" "PROVINCIA"
## [4] "IDE" "identidad" "salud"
## [7] "educacion" "saneamiento" "electrificacion"
## [10] "poblacion" "costa" "capital"
## [13] "tamano"IDE[,c(11:13)]=lapply(IDE[,c(11:13)],as.factor)todas1=lm(salud~identidad+educacion+saneamiento+electrificacion+poblacion+costa+capital+tamano,data=IDE)
summary(todas1)##
## Call:
## lm(formula = salud ~ identidad + educacion + saneamiento + electrificacion +
## poblacion + costa + capital + tamano, data = IDE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -10.3402 -3.2121 -0.2517 2.6801 19.4999
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.176e+00 1.662e+01 0.251 0.8019
## identidad -2.388e-02 1.886e-01 -0.127 0.8994
## educacion 1.140e-02 4.858e-02 0.235 0.8147
## saneamiento 1.351e-01 2.594e-02 5.209 5.07e-07 ***
## electrificacion 2.556e-02 3.751e-02 0.681 0.4965
## poblacion 1.399e-06 4.946e-06 0.283 0.7776
## costaSI 2.171e+00 1.218e+00 1.783 0.0763 .
## capitalSI 7.036e+00 1.546e+00 4.551 9.73e-06 ***
## tamanoMediana -3.462e+00 2.507e+00 -1.381 0.1690
## tamanoMuy grande -1.258e+00 3.940e+01 -0.032 0.9746
## tamanoMuy pequena -3.255e-01 3.043e+00 -0.107 0.9149
## tamanoPequena -2.534e+00 2.859e+00 -0.887 0.3765
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.86 on 183 degrees of freedom
## Multiple R-squared: 0.5837, Adjusted R-squared: 0.5587
## F-statistic: 23.33 on 11 and 183 DF, p-value: < 2.2e-16SI TOMAMOS A IDENTIDAD COMO LA DEPENDIENTE
todas2=lm(identidad~salud+educacion+saneamiento+electrificacion+poblacion+costa+capital+tamano,data=IDE)
summary(todas2)##
## Call:
## lm(formula = identidad ~ salud + educacion + saneamiento + electrificacion +
## poblacion + costa + capital + tamano, data = IDE)
##
## Residuals:
## Min 1Q Median 3Q Max
## -10.1774 -0.8996 0.2286 1.1466 4.0155
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 8.530e+01 1.642e+00 51.935 < 2e-16 ***
## salud -3.668e-03 2.897e-02 -0.127 0.89938
## educacion 1.190e-01 1.689e-02 7.045 3.64e-11 ***
## saneamiento 2.971e-02 1.067e-02 2.785 0.00592 **
## electrificacion -8.407e-03 1.470e-02 -0.572 0.56819
## poblacion 9.183e-07 1.937e-06 0.474 0.63607
## costaSI 1.979e-01 4.812e-01 0.411 0.68139
## capitalSI 2.562e-01 6.391e-01 0.401 0.68898
## tamanoMediana 1.178e+00 9.838e-01 1.198 0.23259
## tamanoMuy grande -6.758e+00 1.543e+01 -0.438 0.66192
## tamanoMuy pequena 1.767e+00 1.185e+00 1.491 0.13777
## tamanoPequena 1.030e+00 1.120e+00 0.920 0.35884
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.905 on 183 degrees of freedom
## Multiple R-squared: 0.4343, Adjusted R-squared: 0.4003
## F-statistic: 12.77 on 11 and 183 DF, p-value: < 2.2e-16SANEAMIENTO Y COSTA:
f1=formula(saneamiento ~ costa)
aggregate(f1, IDE,mean) ## costa saneamiento
## 1 NO 50.97556
## 2 SI 83.20243hasta aqui podemos decir que el saneamiento es mejor en la cosa que en las que no lo son VEAMOS SI ES O NO PARAMETRICO.
ggqqplot(data=IDE,x="saneamiento") + facet_grid(. ~ costa)
# funcion ad-hoc
normalidadTest=function(x) {y =shapiro.test(x);
c(y$statistic, y$p.value)}
# calculando
resultado= aggregate(f1, IDE,
FUN = normalidadTest)
# mostrando resultado
library(knitr)
shapiroTest=as.data.frame(resultado[,2])
names(shapiroTest)=c("SW_Statistic","Probabilidad")
kable(cbind(resultado[1],shapiroTest))| costa | SW_Statistic | Probabilidad |
|---|---|---|
| NO | 0.9949525 | 0.8529651 |
| SI | 0.9580179 | 0.2422331 |
SI SON PARAMETRICAS.
EN ESTE CASO SE USA LA PRUEBA T
t.test(f1,IDE)##
## Welch Two Sample t-test
##
## data: saneamiento by costa
## t = -14.131, df = 73.273, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -36.77164 -27.68210
## sample estimates:
## mean in group NO mean in group SI
## 50.97556 83.20243La H0 (Los promedios de las variable numerica en cada grupo de la dicotómica no se diferencian.) se rechasa al comprobar que el p valor es inferiori a 0.05