2017_congreso med sueno

Paquetes

library("tidyverse")
library("ggthemes")
library("ggplot2")

abro mi df

x <- read.csv("Epworth 5to.csv", header = TRUE, sep=",")
str(x)

'data.frame':   40 obs. of  13 variables:
 $ n        : int  5 6 13 14 16 18 21 22 23 24 ...
 $ Sexo     : Factor w/ 2 levels "F","M": 2 2 2 2 2 2 2 2 2 2 ...
 $ Edad     : int  27 23 22 23 25 24 23 23 22 26 ...
 $ P1       : int  2 2 1 1 2 2 1 2 1 1 ...
 $ P2       : int  1 1 0 0 1 1 2 0 2 0 ...
 $ P3       : int  0 1 1 0 0 2 1 1 0 0 ...
 $ P4       : int  1 2 3 2 2 3 0 2 1 1 ...
 $ P5       : int  1 3 3 3 3 3 3 3 3 2 ...
 $ P6       : int  0 1 1 0 1 3 2 1 1 1 ...
 $ P7       : int  0 1 0 0 0 1 0 0 0 0 ...
 $ P8       : int  0 0 0 0 0 1 0 0 0 0 ...
 $ PT       : int  5 11 9 6 9 16 9 9 8 5 ...
 $ Pje.total: int  0 2 1 0 1 3 1 1 1 0 ...

summary(x)

       n         Sexo        Edad             P1             P2             P3              P4       
 Min.   : 1.00   F:23   Min.   :22.00   Min.   :0.00   Min.   :0.00   Min.   :0.000   Min.   :0.000  
 1st Qu.:10.75   M:17   1st Qu.:22.75   1st Qu.:1.00   1st Qu.:1.00   1st Qu.:0.000   1st Qu.:1.000  
 Median :20.50          Median :24.00   Median :2.00   Median :1.00   Median :0.500   Median :2.000  
 Mean   :20.50          Mean   :24.12   Mean   :1.65   Mean   :1.25   Mean   :0.725   Mean   :1.775  
 3rd Qu.:30.25          3rd Qu.:25.00   3rd Qu.:2.00   3rd Qu.:2.00   3rd Qu.:1.000   3rd Qu.:3.000  
 Max.   :40.00          Max.   :31.00   Max.   :3.00   Max.   :3.00   Max.   :3.000   Max.   :3.000  
       P5            P6            P7             P8              PT          Pje.total   
 Min.   :0.0   Min.   :0.0   Min.   :0.00   Min.   :0.000   Min.   : 3.00   Min.   :0.00  
 1st Qu.:2.0   1st Qu.:1.0   1st Qu.:0.00   1st Qu.:0.000   1st Qu.: 8.00   1st Qu.:1.00  
 Median :3.0   Median :1.0   Median :0.00   Median :0.000   Median : 9.00   Median :1.00  
 Mean   :2.5   Mean   :1.5   Mean   :0.55   Mean   :0.175   Mean   :10.12   Mean   :1.35  
 3rd Qu.:3.0   3rd Qu.:2.0   3rd Qu.:1.00   3rd Qu.:0.000   3rd Qu.:12.25   3rd Qu.:2.00  
 Max.   :3.0   Max.   :3.0   Max.   :3.00   Max.   :1.000   Max.   :20.00   Max.   :3.00  

x %>% 
  group_by(Sexo) %>% 
  summarise(n=n(), Promedio = mean(Edad), DE = sd(Edad)) %>% 
  ungroup()

tabla1 <- x %>% 
  group_by(Sexo) %>% 
  summarise(n=n(), Promedio = mean(Edad), DE = sd(Edad)) %>% 
  ungroup()

write.table(tabla1)

"Sexo" "n" "Promedio" "DE"
"1" "F" 23 24.1739130434783 2.08134951660616
"2" "M" 17 24.0588235294118 2.13514016622136

x %>% 
  group_by(PT) %>% 
  summarise(n=n(), Promedio = mean(Pje.total), DE = sd(Pje.total), Mediana=median(Pje.total)) %>% 
  ungroup()

main=x$PT

Grafico por boxplot entre sexo y Pje.total

boxplot(x$PT~x$Sexo, xlab="Sexo", ylab="Puntaje total", main="Puntaje total segun sexo")

x %>% 
ggplot(aes(x=Sexo, y=PT)) +
  geom_boxplot() +
  theme_economist() +
  ggtitle("Puntaje total segun sexo")

Existe diferencia significativa entre sexo y el puntaje total ??????

t.test(x$Pje.total~x$Sexo)

    Welch Two Sample t-test

data:  x$Pje.total by x$Sexo
t = 1.321, df = 35.888, p-value = 0.1948
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -0.2163477  1.0245318
sample estimates:
mean in group F mean in group M 
       1.521739        1.117647 

Hago tabla

tabla2 <- matrix(c(4, 5, 7, 6, 8, 5, 4, 1), ncol = 4)

Coloco nombres a las columnas y filas

colnames(tabla2) <- c("No presenta", "Leve","Moderada", "Severa")
rownames(tabla2) <- c("Hombre", "Mujer")

Generano la tabla

tabla2

       No presenta Leve Moderada Severa
Hombre           4    7        8      4
Mujer            5    6        5      1

Grafico tabla en mosaico con color

mosaicplot(tabla2, shade=T)

Calculo proporciones

prop.table(tabla2)*100

       No presenta Leve Moderada Severa
Hombre        10.0 17.5     20.0   10.0
Mujer         12.5 15.0     12.5    2.5

d <- prop.table(tabla2)*100

mosaicplot(d, shade = T)

boxplot(tabla2)

Analisis de chi

chisq.test(tabla2)

Chi-squared approximation may be incorrect

    Pearson's Chi-squared test

data:  tabla2
X-squared = 1.8213, df = 3, p-value = 0.6103