Carga la data:
rm(list = ls())
info=file.path('DataFiles','fragilScoresWide.csv')
laData=read.csv(info)
summary(laData$X2021)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 16.20 51.05 69.90 66.86 83.30 111.70
summary(laData$X2022)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 15.10 50.70 68.90 66.12 82.70 111.70
boxplot(laData[,c(2,3)],horizontal = T)
hist(laData$X2021,ylim = c(0,40))
hist(laData$X2022,ylim = c(0,40))
DescTools::Desc(laData$X2021)
## ------------------------------------------------------------------------------
## laData$X2021 (numeric)
##
## length n NAs unique 0s mean meanCI'
## 179 179 0 166 0 66.86 63.39
## 100.0% 0.0% 0.0% 70.33
##
## .05 .10 .25 median .75 .90 .95
## 21.79 31.96 51.05 69.90 83.30 96.68 99.40
##
## range sd vcoef mad IQR skew kurt
## 95.50 23.52 0.35 22.54 32.25 -0.35 -0.61
##
## lowest : 16.2, 16.6, 18.0, 18.4, 18.8
## highest: 108.4, 109.4, 110.7, 110.9, 111.7
##
## ' 95%-CI (classic)
DescTools::Desc(laData$X2022)
## ------------------------------------------------------------------------------
## laData$X2022 (numeric)
##
## length n NAs unique 0s mean meanCI'
## 179 179 0 171 0 66.12 62.62
## 100.0% 0.0% 0.0% 69.62
##
## .05 .10 .25 median .75 .90 .95
## 20.89 30.98 50.70 68.90 82.70 95.50 100.57
##
## range sd vcoef mad IQR skew kurt
## 96.60 23.73 0.36 22.54 32.00 -0.31 -0.62
##
## lowest : 15.1, 15.6, 17.1, 17.5, 18.1
## highest: 108.1, 108.4, 108.4, 110.5, 111.7
##
## ' 95%-CI (classic)
Usemos el formato largo de la data:
info=file.path('DataFiles','fragilScoresLong.csv')
laDataLong=read.csv(info)
DescTools::Desc(laDataLong$Total~laDataLong$Year)
## ------------------------------------------------------------------------------
## laDataLong$Total ~ laDataLong$Year
##
## Summary:
## n pairs: 358, valid: 358 (100.0%), missings: 0 (0.0%), groups: 2
##
##
## 2021 2022
## mean 66.862 66.122
## median 69.900 68.900
## sd 23.523 23.732
## IQR 32.250 32.000
## n 179 179
## np 50.000% 50.000%
## NAs 0 0
## 0s 0 0
##
## Kruskal-Wallis rank sum test:
## Kruskal-Wallis chi-squared = 0.14321, df = 1, p-value = 0.7051
library(ggplot2)
base=ggplot(data=laDataLong)
base + geom_histogram(aes(x=Total)) + facet_grid(Year~.)
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
base + geom_boxplot(aes(y=Total)) + facet_grid(Year~.) + coord_flip()