library(pacman)
semi <- read.csv("semilla.csv")
T2010 <- subset(semi, tiempo = "2010") 
T2013 <- subset(semi, tiempo = "2013")

U3A5

Tabla

knitr::kable(semi)
Kilogramos tiempo
9 T2010
8 T2010
6 T2010
9 T2010
9 T2010
7 T2010
6 T2010
5 T2010
7 T2010
4 T2010
5 T2010
3 T2010
4 T2010
5 T2010
6 T2010
5 T2010
8 T2013
9 T2013
7 T2013
6 T2013
8 T2013
8 T2013
4 T2013
6 T2013
5 T2013
3 T2013
5 T2013
4 T2013
4 T2013
5 T2013
3 T2013
4 T2013

Gráfico de Caja y Bigote:

boxplot(semi$Kilogramos ~ semi$tiempo, col="orange", main = "Gráfico de caja y bigote", xlab="Año", ylab = "Kilogramos")

5 Números de Turkey

fivenum(T2010$Kilogramos)
## [1] 3.0 4.0 5.5 7.5 9.0
fivenum(T2013$Kilogramos)
## [1] 3.0 4.0 5.5 7.5 9.0

Histogramas

hist(T2010$Kilogramos, col = "purple", main = "Año 2010", ylab = "Frecuencia", xlab="Kilogramos")

summary(T2010$Kilogramos)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   3.000   4.000   5.500   5.844   7.250   9.000
hist(T2013$Kilogramos, col = "green", main = "Año 2013", ylab = "Frecuencia", xlab= "Kilogramos")

summary(T2013$Kilogramos)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   3.000   4.000   5.500   5.844   7.250   9.000

Caja y Bigote comparando las desviaciones con gráfico de barra:

op <- par(mfrow = c(1,2), cex.axis= .7, cex.lab= .9)

boxplot(semi$Kilogramos ~ semi$tiempo, col="orange", main = "Gráfico de caja y bigote", xlab="Año", ylab = "Kilogramos")
barplot(tapply(semi$Kilogramos, list(semi$tiempo), mean), beside = T, main = "Gráfico de Barras", col = "orange", xlab="Año", ylab="Kilogramos")

Pruebas de Normalida

Prueba de Normalidad de Shapro-Wil

shapiro.test(T2010$Kilogramos)
## 
##  Shapiro-Wilk normality test
## 
## data:  T2010$Kilogramos
## W = 0.92283, p-value = 0.02482
shapiro.test(T2013$Kilogramos)
## 
##  Shapiro-Wilk normality test
## 
## data:  T2013$Kilogramos
## W = 0.92283, p-value = 0.02482

Prueba de Normalidad de Kolmogorov-Smirnov

ks.test(T2010$Kilogramos, "pnorm", mean=mean(T2010$Kilogramos), sd=sd(T2010$Kilogramos))
## Warning in ks.test(T2010$Kilogramos, "pnorm", mean = mean(T2010$Kilogramos), :
## ties should not be present for the Kolmogorov-Smirnov test
## 
##  One-sample Kolmogorov-Smirnov test
## 
## data:  T2010$Kilogramos
## D = 0.17129, p-value = 0.3048
## alternative hypothesis: two-sided
ks.test(T2013$Kilogramos, "pnorm", mean=mean(T2013$Kilogramos), sd=sd(T2013$Kilogramos))
## Warning in ks.test(T2013$Kilogramos, "pnorm", mean = mean(T2013$Kilogramos), :
## ties should not be present for the Kolmogorov-Smirnov test
## 
##  One-sample Kolmogorov-Smirnov test
## 
## data:  T2013$Kilogramos
## D = 0.17129, p-value = 0.3048
## alternative hypothesis: two-sided

Prueba de T

t.test(T2010$Kilogramos, T2013$Kilogramos, var.equal = T,)
## 
##  Two Sample t-test
## 
## data:  T2010$Kilogramos and T2013$Kilogramos
## t = 0, df = 62, p-value = 1
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.9508204  0.9508204
## sample estimates:
## mean of x mean of y 
##   5.84375   5.84375

Prueba de F

var.test(T2010$Kilogramos, T2013$Kilogramos)
## 
##  F test to compare two variances
## 
## data:  T2010$Kilogramos and T2013$Kilogramos
## F = 1, num df = 31, denom df = 31, p-value = 1
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
##  0.4881425 2.0485820
## sample estimates:
## ratio of variances 
##                  1