Practica 5

file.choose()

[1] "C:\\Users\\Lenovo\\Downloads\\Grado_alcohólico.xlsx"

ruta_Ensamble <-"C:\\Users\\Lenovo\\Downloads\\Grado_alcohólico.xlsx"

excel_sheets(ruta_Ensamble)

[1] "VINOS POR PRUEBA FQ."

casoDBCA1<-read_excel(ruta_Ensamble)

print(casoDBCA1)

#Se crea un objeto tipo factor

GRADO<-factor(Grado_alcohólico$`Grado_alcohólico_volumétrico_%Volumen`)

VAR <-factor(Grado_alcohólico$Variedad)

#Luego el vector TIEM se convierte a un vector ALT1 de tipo numérico

GRADO1<-as.numeric(GRADO)

#Diagrama de cajas de dispersión (Box plot)

par(mfrow=c(1,1))

boxplot(split(GRADO1,VAR),xlab="variedad", ylab="grado de alcohol")

resaov<-aov(GRADO1 ~ VAR)

anova(resaov)

Analysis of Variance Table

Response: GRADO1
          Df  Sum Sq Mean Sq F value Pr(>F)
VAR        6  339.71  56.619  0.7115 0.6438
Residuals 24 1909.96  79.582               

cv.model(resaov)

[1] 57.37486

euc.lm <- lm(GRADO1 ~ VAR)

anova(euc.lm , test="F")

Analysis of Variance Table

Response: GRADO1
          Df  Sum Sq Mean Sq F value Pr(>F)
VAR        6  339.71  56.619  0.7115 0.6438
Residuals 24 1909.96  79.582               

shapiro.test(euc.lm$res)

    Shapiro-Wilk normality test

data:  euc.lm$res
W = 0.96325, p-value = 0.3548

fitb <- fitted(resaov)

res_stb <- rstandard(resaov)

plot(fitb,res_stb,xlab="Valores predichos", ylab="valores estandarizados",abline(h=0))

5.- Prueba de homocedasticidad (homogeneidad de las varianzas) #Prueba de Bartlett

#Prueba de Levene

leveneTest(GRADO1 ~ VAR, center = "median")

Levene's Test for Homogeneity of Variance (center = "median")
      Df F value Pr(>F)
group  6  0.3228 0.9185
      24               

6.- Pruebas de comparación múltiple de medias #Método de la diferencia mínima significativa, Least Significant Difference (LSD)

outLSD <-LSD.test(resaov, "VAR",console=TRUE)

Study: resaov ~ "VAR"

LSD t Test for GRADO1 

Mean Square Error:  79.58183 

VAR,  means and individual ( 95 %) CI

Alpha: 0.05 ; DF Error: 24
Critical Value of t: 2.063899 

Groups according to probability of means differences and alpha level( 0.05 )

Treatments with the same letter are not significantly different.

outHSD<-HSD.test(resaov, "VAR",console=TRUE)

Study: resaov ~ "VAR"

HSD Test for GRADO1 

Mean Square Error:  79.58183 

VAR,  means

Alpha: 0.05 ; DF Error: 24 
Critical Value of Studentized Range: 4.541314 

Groups according to probability of means differences and alpha level( 0.05 )

Treatments with the same letter are not significantly different.

SNK.test(resaov, "VAR",console=TRUE)

Study: resaov ~ "VAR"

Student Newman Keuls Test
for GRADO1 

Mean Square Error:  79.58183 

VAR,  means

Groups according to probability of means differences and alpha level( 0.05 )

Means with the same letter are not significantly different.

scheffe.test(resaov, "VAR",console=TRUE)

Study: resaov ~ "VAR"

Scheffe Test for GRADO1 

Mean Square Error  : 79.58183 

VAR,  means

Alpha: 0.05 ; DF Error: 24 
Critical Value of F: 2.508189 

Groups according to probability of means differences and alpha level( 0.05 )

Means with the same letter are not significantly different.

duncan.test(resaov, "VAR",console=TRUE)

Study: resaov ~ "VAR"

Duncan's new multiple range test
for GRADO1 

Mean Square Error:  79.58183 

VAR,  means

Groups according to probability of means differences and alpha level( 0.05 )

Means with the same letter are not significantly different.

LSD.test(resaov, "VAR", p.adj= "bon",console=TRUE)

Study: resaov ~ "VAR"

LSD t Test for GRADO1 
P value adjustment method: bonferroni 

Mean Square Error:  79.58183 

VAR,  means and individual ( 95 %) CI

Alpha: 0.05 ; DF Error: 24
Critical Value of t: 3.395988 

Groups according to probability of means differences and alpha level( 0.05 )

Treatments with the same letter are not significantly different.

sk <- SK(resaov, which= "VAR",  dispersion="se", sig.level=0.05)

summary(sk)