Práctica Calificada Bivariado
Raul Salinas Prieto
15020410
linkFreedom="https://en.wikipedia.org/wiki/List_of_freedom_indices"
pathFreedom='//*[@id="mw-content-text"]/div[1]/table[2]'
Freedom=htmltab::htmltab(linkFreedom, pathFreedom)names(Freedom)=c("Country", "Free", "EconomicFree", "FreePress", "Regime")
names(Freedom)## [1] "Country" "Free" "EconomicFree" "FreePress"
## [5] "Regime"str(Freedom)## 'data.frame': 198 obs. of 5 variables:
## $ Country : chr " Afghanistan" " Albania" " Algeria" " Andorra" ...
## $ Free : chr "not free" "partly free" "not free" "free" ...
## $ EconomicFree: chr "mostly unfree" "moderately free" "repressed" "n/a" ...
## $ FreePress : chr "difficult situation" "noticeable problems" "difficult situation" "satisfactory situation" ...
## $ Regime : chr "authoritarian regime" "hybrid regime" "hybrid regime" "n/a" ...Freedom$EconomicFree=as.ordered(Freedom$EconomicFree)
Freedom$Free=as.ordered(Freedom$Free)
str(Freedom)## 'data.frame': 198 obs. of 5 variables:
## $ Country : chr " Afghanistan" " Albania" " Algeria" " Andorra" ...
## $ Free : Ord.factor w/ 4 levels "free"<"n/a"<"not free"<..: 3 4 3 1 3 1 1 4 1 1 ...
## $ EconomicFree: Ord.factor w/ 6 levels "free"<"moderately free"<..: 4 2 6 5 4 5 4 3 1 3 ...
## $ FreePress : chr "difficult situation" "noticeable problems" "difficult situation" "satisfactory situation" ...
## $ Regime : chr "authoritarian regime" "hybrid regime" "hybrid regime" "n/a" ...columna=Freedom$Free
fila=Freedom$EconomicFree
(t=table(fila,columna))## columna
## fila free n/a not free partly free
## free 4 0 0 2
## moderately free 26 0 9 27
## mostly free 24 1 3 3
## mostly unfree 15 0 19 28
## n/a 11 0 7 0
## repressed 3 0 12 4(prop_t=prop.table(t,margin = 2))## columna
## fila free n/a not free partly free
## free 0.04819277 0.00000000 0.00000000 0.03125000
## moderately free 0.31325301 0.00000000 0.18000000 0.42187500
## mostly free 0.28915663 1.00000000 0.06000000 0.04687500
## mostly unfree 0.18072289 0.00000000 0.38000000 0.43750000
## n/a 0.13253012 0.00000000 0.14000000 0.00000000
## repressed 0.03614458 0.00000000 0.24000000 0.06250000library(gplots)##
## Attaching package: 'gplots'## The following object is masked from 'package:stats':
##
## lowess# nota que uso la funcion "t()":
balloonplot(t(prop_t), main ="tabla",
label = T, show.margins = FALSE)
chisq.test(t)## Warning in chisq.test(t): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: t
## X-squared = 62.144, df = 15, p-value = 1.076e-07library(oii)
association.measures(fila,columna)## Chi-square-based measures of association:
## Phi: 0.560
## Contingency coefficient: 0.489
## Cramer's V: 0.323
##
## Ordinal measures of association:
## Total number of pairs: 19503
## Concordant pairs: 5240 ( 26.87 %)
## Discordant pairs: 4839 ( 24.81 %)
## Tied on first variable: 2780 ( 14.25 %)
## Tied on second variable: 4838 ( 24.81 %)
## Tied on both variables: 1806 ( 9.26 %)
##
## Goodman-Kruskal Gamma: 0.040
## Somers' d (col dep.): 0.027
## Kendall's tau-b: 0.029
## Stuart's tau-c: 0.027columna=Freedom$Regime
fila=Freedom$EconomicFree
(t=table(fila,columna))## columna
## fila authoritarian regime flawed democracy full democracy
## free 0 2 4
## moderately free 9 24 5
## mostly free 3 12 13
## mostly unfree 25 14 0
## n/a 5 0 0
## repressed 12 2 0
## columna
## fila hybrid regime n/a
## free 0 0
## moderately free 14 10
## mostly free 2 1
## mostly unfree 17 6
## n/a 0 13
## repressed 4 1(prop_t=prop.table(t,margin = 2))## columna
## fila authoritarian regime flawed democracy full democracy
## free 0.00000000 0.03703704 0.18181818
## moderately free 0.16666667 0.44444444 0.22727273
## mostly free 0.05555556 0.22222222 0.59090909
## mostly unfree 0.46296296 0.25925926 0.00000000
## n/a 0.09259259 0.00000000 0.00000000
## repressed 0.22222222 0.03703704 0.00000000
## columna
## fila hybrid regime n/a
## free 0.00000000 0.00000000
## moderately free 0.37837838 0.32258065
## mostly free 0.05405405 0.03225806
## mostly unfree 0.45945946 0.19354839
## n/a 0.00000000 0.41935484
## repressed 0.10810811 0.03225806library(gplots)
# nota que uso la funcion "t()":
balloonplot(t(prop_t), main ="tabla",
label = T, show.margins = FALSE)
chisq.test(t)## Warning in chisq.test(t): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: t
## X-squared = 141.88, df = 20, p-value < 2.2e-16library(oii)
association.measures(fila,columna)## Chi-square-based measures of association:
## Phi: 0.846
## Contingency coefficient: 0.646
## Cramer's V: 0.423
##
## Ordinal measures of association:
## Total number of pairs: 19503
## Concordant pairs: 5352 ( 27.44 %)
## Discordant pairs: 6657 ( 34.13 %)
## Tied on first variable: 3270 ( 16.77 %)
## Tied on second variable: 2908 ( 14.91 %)
## Tied on both variables: 1316 ( 6.75 %)
##
## Goodman-Kruskal Gamma: -0.109
## Somers' d (col dep.): -0.087
## Kendall's tau-b: -0.086
## Stuart's tau-c: -0.083LinkDemo="https://en.wikipedia.org/wiki/Democracy_Index"
pathDemo='//*[@id="mw-content-text"]/div[1]/table[2]'
Demo=htmltab::htmltab(LinkDemo, pathDemo)Demo=Demo[,-c(1, 3, 11)]
names(Demo)=c("country", "elec", "funct", "partic", "cult", "civil", "regime", "region")
names(Demo)## [1] "country" "elec" "funct" "partic" "cult" "civil" "regime"
## [8] "region"str(Demo)## 'data.frame': 167 obs. of 8 variables:
## $ country: chr " Norway" " Iceland" " Sweden" " New Zealand" ...
## $ elec : chr "10.00" "10.00" "9.58" "10.00" ...
## $ funct : chr "9.64" "9.29" "9.64" "9.29" ...
## $ partic : chr "10.00" "8.89" "8.33" "8.89" ...
## $ cult : chr "10.00" "10.00" "10.00" "8.13" ...
## $ civil : chr "9.71" "9.71" "9.41" "10.00" ...
## $ regime : chr "Full democracy" "Full democracy" "Full democracy" "Full democracy" ...
## $ region : chr "Western Europe" "Western Europe" "Western Europe" "Asia & Australasia" ...Demo[,2:6]=lapply(Demo[,2:6],as.numeric)str(Demo)## 'data.frame': 167 obs. of 8 variables:
## $ country: chr " Norway" " Iceland" " Sweden" " New Zealand" ...
## $ elec : num 10 10 9.58 10 10 10 10 9.58 10 9.58 ...
## $ funct : num 9.64 9.29 9.64 9.29 8.93 7.86 9.29 9.64 8.93 9.29 ...
## $ partic : num 10 8.89 8.33 8.89 8.89 8.33 8.33 7.78 7.78 7.78 ...
## $ cult : num 10 10 10 8.13 8.75 10 9.38 9.38 8.75 9.38 ...
## $ civil : num 9.71 9.71 9.41 10 9.71 10 9.12 9.71 10 9.12 ...
## $ regime : chr "Full democracy" "Full democracy" "Full democracy" "Full democracy" ...
## $ region : chr "Western Europe" "Western Europe" "Western Europe" "Asia & Australasia" ...fcatnum=formula(cult ~ region)
aggregate(fcatnum, Demo,mean) ## region cult
## 1 Asia & Australasia 5.493571
## 2 Eastern Europe 4.935357
## 3 Latin America 5.262917
## 4 Middle East & North Africa 4.753000
## 5 North America 8.440000
## 6 Sub-Saharan Africa 5.230227
## 7 Western Europe 8.097143library(ggpubr)## Loading required package: ggplot2## Loading required package: magrittrp1=ggscatter(Demo,
x = "partic", y = "cult",
cor.coef = TRUE,
cor.method = "pearson")
p1
s4=ggscatter(Demo,
x = "partic", y = "cult",
cor.coef = TRUE,
cor.method = "spearman")
s4
En las dos últimas me equivoqué y era “spearman” y el coeficiente de correlación era 0.53.