Crear un vector de paquetes
pacotes <- c("agricolae", "ggplot2", "outliers", "tidyverse", "nortest", "stats", "performance")
Script para instalar y cargar librerias y dependencias
if(sum(as.numeric(!pacotes %in% installed.packages())) != 0){
instalador <- pacotes[!pacotes %in% installed.packages()]
for(i in 1:length(instalador)) {
install.packages(instalador, dependencies = T)
break()}
sapply(pacotes, require, character = T)
} else {
sapply(pacotes, require, character = T)
}
## Loading required package: agricolae
## Loading required package: ggplot2
## Loading required package: outliers
## Loading required package: tidyverse
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
## Loading required package: nortest
##
## Loading required package: performance
## agricolae ggplot2 outliers tidyverse nortest stats
## TRUE TRUE TRUE TRUE TRUE TRUE
## performance
## TRUE
data(potato)
?potato
## starting httpd help server ... done
Análisis exploratório ——
Crear un gráfico de cajas (boxplot) de las variedades por
“corte”
ggplot(data = potato, aes(x = variety, y = cutting)) +
geom_boxplot(fill = "lightblue") +
labs(x = "Variedad", y = "Corte") +
ggtitle("Rendimiento de Dos variedades de Papa")+
theme_bw()
Valores atípicos (outlier)
potato%>%
select_if(is.numeric)%>%
outlier()
## date harvest cutting
## 18.0000 3.0000 9.8125
View(potato)
ANOVA DCA ——— aov= Analisis Of Variance
model_DCA<-aov(cutting~variety,data=potato)
summary(model_DCA)
## Df Sum Sq Mean Sq F value Pr(>F)
## variety 1 25.09 25.087 6.665 0.0201 *
## Residuals 16 60.22 3.764
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cv.model(model_DCA)
## [1] 37.76287
Verificación de supuestos ————
Normalidad ——————–
Verificar la normalidad de los residuos (Prueba de
Shapiro-Wilk)
residuals(model_DCA)
## 1 2 3 4 5 6
## -1.18194444 -1.60694444 0.21805556 -1.39444444 -0.39444444 -0.58194444
## 7 8 9 10 11 12
## 0.79305556 1.51180556 2.63680556 -3.71805556 -1.04305556 -0.51805556
## 13 14 15 16 17 18
## -1.81805556 0.86944444 -0.66180556 -0.06805556 3.49444444 3.46319444
shapiro.test(residuals(model_DCA))
##
## Shapiro-Wilk normality test
##
## data: residuals(model_DCA)
## W = 0.94913, p-value = 0.4116
Prueba de normalidad de Kolmogorov-Smirnov
ks.test(residuals(model_DCA),
"pnorm",
mean = mean(residuals(model_DCA)),
sd = sd(residuals(model_DCA)))
##
## Exact one-sample Kolmogorov-Smirnov test
##
## data: residuals(model_DCA)
## D = 0.13855, p-value = 0.8343
## alternative hypothesis: two-sided
Prueba de normalidad de Anderson-Darling. # Cargar la librería
‘nortest’ para la función ‘ad.test’
library(nortest)
ad.test(residuals(model_DCA))
##
## Anderson-Darling normality test
##
## data: residuals(model_DCA)
## A = 0.42351, p-value = 0.2852
Crear un gráfico de qq-plot para evaluar la normalidad
qqnorm(residuals(model_DCA))
qqnorm(residuals(model_DCA))
qqline(residuals(model_DCA))
Homogeneidad de varianza (Prueba de Levene) ———–
Cargar la librería ‘car’ para la función ‘leveneTest’
library(car)
## Loading required package: carData
##
## Attaching package: 'car'
## The following object is masked from 'package:dplyr':
##
## recode
## The following object is masked from 'package:purrr':
##
## some
leveneTest(model_DCA)
## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 1 0.8149 0.3801
## 16
Crear un gráfico de dispersión de residuos frente a los niveles del
factor
ggplot(data = potato, aes(x = variety,
y = residuals(model_DCA))) +
geom_point() +
labs(x = "Variedad", y = "residuos") +
ggtitle("Gráfico de Dispersión de Residuos Según
las Variedades de Papa")+
theme_bw()
Supuestos de normalidad en un solo código
check_model(model_DCA)
ANOVA DCA ———
model_DCA<-aov(cutting~variety,data=potato)
summary(model_DCA)
## Df Sum Sq Mean Sq F value Pr(>F)
## variety 1 25.09 25.087 6.665 0.0201 *
## Residuals 16 60.22 3.764
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
cv.model(model_DCA)
## [1] 37.76287
Realizar la prueba de Tukey
tukey_result <- TukeyHSD(model_DCA)
tukey_result
## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = cutting ~ variety, data = potato)
##
## $variety
## diff lwr upr p adj
## Unica-Canchan -2.361111 -4.299884 -0.4223378 0.0200726
Realiza la prueba de Tukey para el modelo ANOVA
tukey_result <- HSD.test(model_DCA, "variety")
Muestra los grupos caracterizados por letras
tukey_result
## $statistics
## MSerror Df Mean CV MSD
## 3.763862 16 5.1375 37.76287 1.938773
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey variety 2 2.997999 0.05
##
## $means
## cutting std r se Min Max Q25 Q50 Q75
## Canchan 6.318056 2.342248 9 0.6466892 2.60 9.81250 5.275 5.8000 7.1875
## Unica 3.956944 1.428844 9 0.6466892 2.35 6.59375 2.775 3.5625 4.7500
##
## $comparison
## NULL
##
## $groups
## cutting groups
## Canchan 6.318056 a
## Unica 3.956944 b
##
## attr(,"class")
## [1] "group"
Realiza la prueba de Tukey para el modelo ANOVA
tukey_result_alfa_0.01 <- HSD.test(model_DCA, "variety", alpha = 0.01)
Muestra los grupos caracterizados por letras
tukey_result_alfa_0.01
## $statistics
## MSerror Df Mean CV MSD
## 3.763862 16 5.1375 37.76287 2.67122
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey variety 2 4.130609 0.01
##
## $means
## cutting std r se Min Max Q25 Q50 Q75
## Canchan 6.318056 2.342248 9 0.6466892 2.60 9.81250 5.275 5.8000 7.1875
## Unica 3.956944 1.428844 9 0.6466892 2.35 6.59375 2.775 3.5625 4.7500
##
## $comparison
## NULL
##
## $groups
## cutting groups
## Canchan 6.318056 a
## Unica 3.956944 a
##
## attr(,"class")
## [1] "group"
Gráfico de barras ———————–
bar.group(tukey_result_alfa_0.01$groups, ylim=c(0,10),
col=9:6, ylab = "Cortes",
main = "Evaluación de Dos Variedades de Papa")
box()
data <- tukey_result_alfa_0.01$groups
data$variedad <- row.names(tukey_result_alfa_0.01$groups)
Crear el gráfico de barras
library(plotly)
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
library(ggrepel)
ggplot(data = potato, aes(x = variety, y = cutting, fill = harvest)) +
geom_bar(stat = "identity", position = "dodge") +
labs(x = "Variedad", y = "corte", fill = "Grupos") +
ggtitle("Evaluación de Dos Variedades de Papa") +
theme_bw()
Etiquetas personalizadas
etiquetas <- c( "Variedad Canchan", "Variedad Única")
Crear el gráfico de barras con etiquetas personalizadas
ggplot(data = potato, aes(x = variety, y = cutting, fill = harvest)) +
geom_bar(stat = "identity", position = "dodge") +
scale_x_discrete(labels = etiquetas) +
labs(x = "Variedad", y = "corte", fill = "Grupos") +
ggtitle("Evaluación de Dos Variedades de Papa") +
theme_bw()
data
## cutting groups variedad
## Canchan 6.318056 a Canchan
## Unica 3.956944 a Unica
Crear el gráfico de barras con etiquetas personalizadas y letras en
la parte superior
ggplot(data = potato, aes(x = variety, y = cutting, fill = harvest)) +
geom_bar(stat = "identity", position = "dodge") +
scale_x_discrete(labels = etiquetas) +
geom_text(aes(label = harvest), vjust = 1.0,
position = position_dodge(width = 0.1)) +
labs(x = "Variedad", y = "corte", fill = "Grupos") +
ggtitle("Evaluación de Dos Variedades de Papa") +
theme_bw()
