asd

library(readxl)

## Warning: package 'readxl' was built under R version 3.4.2

DATOS_BIOSTA <- read_excel("C:/Users/usuario/Desktop/DATOS BIOSTA.xlsx", 
    sheet = "Hoja1")
View(DATOS_BIOSTA)

attach(DATOS_BIOSTA)
tapply(Promedio_global,Nivel,mean)

##        1        2        3        4        5        6 
## 7.858750 7.356923 7.076667 8.525000 8.320000 7.400000

tapply(Promedio_global,Nivel,sd)

##         1         2         3         4         5         6 
## 0.8846054 0.8047348 0.8169938 0.3889087        NA        NA

tapply(Promedio_global,Nivel,length)

##  1  2  3  4  5  6 
##  8 26 12  2  1  1

anova<-aov(Promedio_global~Nivel)
summary(anova)

##             Df Sum Sq Mean Sq F value Pr(>F)
## Nivel        1   0.01  0.0146    0.02  0.889
## Residuals   48  35.44  0.7384

shapiro.test(residuals(anova))

## 
##  Shapiro-Wilk normality test
## 
## data:  residuals(anova)
## W = 0.98499, p-value = 0.7713

library(car)

## Warning: package 'car' was built under R version 3.4.2

levene.test(Promedio_global~as.factor(Nivel))

## Warning: 'levene.test' is deprecated.
## Use 'leveneTest' instead.
## See help("Deprecated") and help("car-deprecated").

## Levene's Test for Homogeneity of Variance (center = median)
##       Df F value Pr(>F)
## group  5  0.7887 0.5635
##       44

drop1(anova,test = "F")

## Single term deletions
## 
## Model:
## Promedio_global ~ Nivel
##        Df Sum of Sq    RSS     AIC F value Pr(>F)
## <none>              35.443 -13.205               
## Nivel   1  0.014618 35.457 -15.184  0.0198 0.8887

Se encontró que el 4to nivel posee el promedio mas alto con una media de (8.52,±0.38,n=2) Consecuentemente se comprobo que el nivel 3 posee el promedio mas bajo con una media de (7.07,±0,81,n=12)