Contexto

El objetivo fue evaluar la calidad de fibra de las alpacas del distrito de Cojata, provincia de Huancané de la región Puno; para ello, se recolectó 1759 muestras de fibra del costillar medio, las cuales fueron analizadas en OFDA2000 bajo el modo de mecha grasienta. El estudio desea saber si los factores Sexo, Edad, Zona, Estrato y Comunidad tienen efecto sobre las medias de las características físicas de la fibra.

Cargar Librerías

# Cargar paquetes
library(readxl)
library(dplyr)
library(ggplot2)
library(skimr)
library(car)
library(FSA)
library(dunn.test)
library(Hmisc)

Cargar Dataset

# Cargar datos
datos <- read_excel("COJATA.xlsx")
datos

Análisis Exploratorio de datos

# Obtener un resumen general de los datos
skim(datos)
Data summary
Name datos
Number of rows 1759
Number of columns 12
_______________________
Column type frequency:
character 5
numeric 7
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
Sexo 0 1 5 6 0 2 0
Edad 0 1 1 1 0 4 0
Zona 0 1 3 6 0 3 0
Estrato 0 1 4 5 0 3 0
Comunidad 0 1 4 10 0 9 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
Altura 0 1 4362.59 67.63 4119.00 4339.00 4359.00 4406.00 4482.00 ▁▁▂▇▃
Has 0 1 81.53 36.11 29.00 55.00 80.00 100.00 218.00 ▅▇▁▁▁
DMF 0 1 20.46 2.81 13.39 18.34 20.24 22.30 31.19 ▂▇▆▂▁
DSD 0 1 4.23 0.69 0.00 3.75 4.17 4.66 7.83 ▁▁▇▂▁
CVD 0 1 20.69 2.06 0.00 19.40 20.60 22.00 27.30 ▁▁▁▇▃
FC 0 1 95.72 5.83 50.60 94.35 97.70 99.40 100.00 ▁▁▁▁▇
IC 0 1 41.37 7.50 8.00 36.10 41.00 46.25 75.00 ▁▂▇▂▁ 
# Visualizar las primeras filas
head(datos)
# Resumen de variables numéricas
summary(datos[, c("DMF", "DSD", "CVD", "FC", "IC")])
##       DMF             DSD             CVD              FC        
##  Min.   :13.39   Min.   :0.000   Min.   : 0.00   Min.   : 50.60  
##  1st Qu.:18.34   1st Qu.:3.750   1st Qu.:19.40   1st Qu.: 94.35  
##  Median :20.24   Median :4.170   Median :20.60   Median : 97.70  
##  Mean   :20.46   Mean   :4.227   Mean   :20.69   Mean   : 95.72  
##  3rd Qu.:22.30   3rd Qu.:4.660   3rd Qu.:22.00   3rd Qu.: 99.40  
##  Max.   :31.19   Max.   :7.830   Max.   :27.30   Max.   :100.00  
##        IC       
##  Min.   : 8.00  
##  1st Qu.:36.10  
##  Median :41.00  
##  Mean   :41.37  
##  3rd Qu.:46.25  
##  Max.   :75.00
# Gráficos de dispersión para variables numéricas
plot(datos$DMF, datos$DSD, pch = 19, col = "steelblue")

plot(datos$DMF, datos$FC, pch = 19, col = "brown")

plot(datos$DMF, datos$IC, pch = 19, col = "darkorange")

plot(datos$DMF, datos$CVD, pch = 19, col = "red")

# Gráficos de densidad para variables numéricas
ggplot(datos, aes(x = DMF)) + geom_density(fill = "steelblue", alpha = 0.5) + theme_minimal()

ggplot(datos, aes(x = DSD)) + geom_density(fill = "darkgreen", alpha = 0.5) + theme_minimal()

ggplot(datos, aes(x = CVD)) + geom_density(fill = "darkorange", alpha = 0.5) + theme_minimal()

ggplot(datos, aes(x = FC)) + geom_density(fill = "purple", alpha = 0.5) + theme_minimal()

ggplot(datos, aes(x = IC)) + geom_density(fill = "darkred", alpha = 0.5) + theme_minimal()

# Gráficos de barras para variables categóricas
ggplot(datos, aes(x = Comunidad, fill = Comunidad)) + geom_bar() + theme_minimal() + 
  scale_fill_manual(values = c("steelblue", "green", "darkorange", "purple", "darkred", "gray", "darkblue","brown", "darkgray"))

ggplot(datos, aes(x = Sexo, fill = Sexo)) + geom_bar() + theme_minimal() + 
  scale_fill_manual(values = c("steelblue", "darkorange"))

ggplot(datos, aes(x = Estrato, fill = Estrato)) + geom_bar() + theme_minimal() + 
  scale_fill_manual(values = c("steelblue", "gray", "darkorange"))

ggplot(datos, aes(x = Zona, fill = Zona)) + geom_bar() + theme_minimal() + 
  scale_fill_manual(values = c("steelblue", "darkorange", "gray"))

ggplot(datos, aes(x = Edad, fill = Edad)) + geom_bar() + theme_minimal() + 
  scale_fill_manual(values = c("steelblue", "gray", "darkorange", "darkred"))

# Tablas de frecuencias para variables categóricas
table(datos$Comunidad)
## 
##    Chajana Huancasaya       Japo Koricancha  Los Andes Mallcunuta     Mecani 
##        198        191        195        195        196        198        196 
## Tomapirhua   Umabamba 
##        197        193
table(datos$Sexo)
## 
## Hembra  Macho 
##   1343    416
table(datos$Estrato)
## 
##  Alto  Bajo Medio 
##   503   504   752
table(datos$Zona)
## 
## Centro  Norte    Sur 
##    588    591    580
table(datos$Edad)
## 
##   A   B   C   D 
## 431 452 438 438

Prueba de Normalidad y Homocedasticidad

# Seleccionar solo las variables numéricas
datos_numericos <- datos[, c("DMF", "DSD", "CVD", "FC", "IC")]

# Prueba de normalidad de Shapiro-Wilk
shapiro_test <- apply(datos_numericos, 2, shapiro.test)

# Gráficos de normalidad
par(mfrow = c(2, 3))
for (i in seq_along(datos_numericos)) {
  variable <- colnames(datos_numericos)[i]
  qqnorm(datos_numericos[[i]], main = paste("Q-Q Plot de", variable), col = "steelblue")
  qqline(datos_numericos[[i]], col = "darkred")
}

# Imprimir resultados de la prueba de Shapiro-Wilk
print(shapiro_test)
## $DMF
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.98381, p-value = 3.369e-13
## 
## 
## $DSD
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.97743, p-value = 5.022e-16
## 
## 
## $CVD
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.95468, p-value < 2.2e-16
## 
## 
## $FC
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.69709, p-value < 2.2e-16
## 
## 
## $IC
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.99233, p-value = 5.972e-08
library(car)

# Seleccionar solo las variables numéricas
datos_numericos <- datos[, c("DMF", "DSD", "CVD", "FC", "IC")]

# Prueba de normalidad de Shapiro-Wilk
shapiro_test <- apply(datos_numericos, 2, shapiro.test)

# Gráficos de normalidad
par(mfrow = c(2, 3))

for (i in seq_along(datos_numericos)) {
  variable <- colnames(datos_numericos)[i]
  qqnorm(datos_numericos[[i]], main = paste("Q-Q Plot de", variable), col = "steelblue")
  qqline(datos_numericos[[i]], col = "red")
}

# Imprimir resultados de la prueba de Shapiro-Wilk
print(shapiro_test)
## $DMF
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.98381, p-value = 3.369e-13
## 
## 
## $DSD
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.97743, p-value = 5.022e-16
## 
## 
## $CVD
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.95468, p-value < 2.2e-16
## 
## 
## $FC
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.69709, p-value < 2.2e-16
## 
## 
## $IC
## 
##  Shapiro-Wilk normality test
## 
## data:  newX[, i]
## W = 0.99233, p-value = 5.972e-08
# Prueba de homogeneidad de varianzas de Levene
levene_test <- lapply(datos_numericos, function(x) leveneTest(x ~ datos$Comunidad, data = datos))
## Warning in leveneTest.default(y = y, group = group, ...): group coerced to
## factor.
## Warning in leveneTest.default(y = y, group = group, ...): group coerced to
## factor.
## Warning in leveneTest.default(y = y, group = group, ...): group coerced to
## factor.
## Warning in leveneTest.default(y = y, group = group, ...): group coerced to
## factor.
## Warning in leveneTest.default(y = y, group = group, ...): group coerced to
## factor.
# Gráficos de dispersión de residuos
par(mfrow = c(2, 3))

for (i in seq_along(datos_numericos)) {
  variable <- colnames(datos_numericos)[i]
  residuos <- residuals(lm(datos_numericos[[i]] ~ datos$Comunidad))
  plot(fitted(lm(datos_numericos[[i]] ~ datos$Comunidad)), residuos, main = paste("Dispersión de residuos de", variable), col = "steelblue", pch = 19)
  abline(h = 0, col = "red")
}

# Imprimir resultados de la prueba de Levene
print(levene_test)
## $DMF
## Levene's Test for Homogeneity of Variance (center = median)
##         Df F value  Pr(>F)  
## group    8  1.8718 0.06039 .
##       1750                  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## $DSD
## Levene's Test for Homogeneity of Variance (center = median)
##         Df F value  Pr(>F)  
## group    8  2.4719 0.01154 *
##       1750                  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## $CVD
## Levene's Test for Homogeneity of Variance (center = median)
##         Df F value Pr(>F)
## group    8  0.8178 0.5868
##       1750               
## 
## $FC
## Levene's Test for Homogeneity of Variance (center = median)
##         Df F value    Pr(>F)    
## group    8  8.1983 6.066e-11 ***
##       1750                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## $IC
## Levene's Test for Homogeneity of Variance (center = median)
##         Df F value Pr(>F)
## group    8  1.5506  0.135
##       1750

Correlograma

# Calcular matriz de correlaciones y valores p
matriz_correlaciones <- cor(datos[, c("DMF", "DSD", "CVD", "FC", "IC")])
p_values <- rcorr(as.matrix(datos[, c("DMF", "DSD", "CVD", "FC", "IC")]))$P

# Convertir la matriz en un dataframe
df_correlaciones <- reshape2::melt(matriz_correlaciones)
df_p_values <- reshape2::melt(p_values)

# Combinar valores de correlaciones y valores p
df_combined <- merge(df_correlaciones, df_p_values, by = c("Var1", "Var2"))
names(df_combined) <- c("Var1", "Var2", "Correlation", "P_Value")

# Crear heatmap de la matriz de correlaciones con valores p
heatmap_correlaciones <- ggplot(data = df_combined, aes(x = Var1, y = Var2, fill = Correlation)) +
  geom_tile() +
  scale_fill_gradient(low = "white", high = "steelblue") +
  labs(title = "Correlograma de características de fibra",
       x = "", y = "") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  geom_text(aes(label = ifelse(P_Value < 0.05, paste(round(Correlation, 2), "***"), round(Correlation, 2))),
            color = "black", size = 3)

# Imprimir el heatmap
print(heatmap_correlaciones)
## Warning: Removed 5 rows containing missing values or values outside the scale range
## (`geom_text()`).

Prueba No Paramétrica Kruskal Wallis

# Prueba de Kruskal-Wallis
kruskal_test <- lapply(datos_numericos, function(x) kruskal.test(x ~ datos$Comunidad, data = datos))

kruskal_test2 <- lapply(datos_numericos, function(x) kruskal.test(x ~ datos$Sexo, data = datos))

kruskal_test3 <- lapply(datos_numericos, function(x) kruskal.test(x ~ datos$Edad, data = datos))

kruskal_test4 <- lapply(datos_numericos, function(x) kruskal.test(x ~ datos$Estrato, data = datos))

kruskal_test5 <- lapply(datos_numericos, function(x) kruskal.test(x ~ datos$Zona, data = datos))

# Imprimir resultados de la prueba de Kruskal-Wallis
print(kruskal_test)
## $DMF
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Comunidad
## Kruskal-Wallis chi-squared = 86.126, df = 8, p-value = 2.836e-15
## 
## 
## $DSD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Comunidad
## Kruskal-Wallis chi-squared = 84.513, df = 8, p-value = 6.01e-15
## 
## 
## $CVD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Comunidad
## Kruskal-Wallis chi-squared = 53.865, df = 8, p-value = 7.332e-09
## 
## 
## $FC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Comunidad
## Kruskal-Wallis chi-squared = 85.712, df = 8, p-value = 3.439e-15
## 
## 
## $IC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Comunidad
## Kruskal-Wallis chi-squared = 50.791, df = 8, p-value = 2.879e-08
# Imprimir resultados de la prueba de Kruskal-Wallis
print(kruskal_test2)
## $DMF
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Sexo
## Kruskal-Wallis chi-squared = 24.298, df = 1, p-value = 8.253e-07
## 
## 
## $DSD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Sexo
## Kruskal-Wallis chi-squared = 5.3903, df = 1, p-value = 0.02025
## 
## 
## $CVD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Sexo
## Kruskal-Wallis chi-squared = 9.3683, df = 1, p-value = 0.002208
## 
## 
## $FC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Sexo
## Kruskal-Wallis chi-squared = 18.867, df = 1, p-value = 1.402e-05
## 
## 
## $IC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Sexo
## Kruskal-Wallis chi-squared = 7.861, df = 1, p-value = 0.005051
# Imprimir resultados de la prueba de Kruskal-Wallis
print(kruskal_test3)
## $DMF
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Edad
## Kruskal-Wallis chi-squared = 431.72, df = 3, p-value < 2.2e-16
## 
## 
## $DSD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Edad
## Kruskal-Wallis chi-squared = 199.73, df = 3, p-value < 2.2e-16
## 
## 
## $CVD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Edad
## Kruskal-Wallis chi-squared = 37.938, df = 3, p-value = 2.913e-08
## 
## 
## $FC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Edad
## Kruskal-Wallis chi-squared = 384.38, df = 3, p-value < 2.2e-16
## 
## 
## $IC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Edad
## Kruskal-Wallis chi-squared = 94.689, df = 3, p-value < 2.2e-16
# Imprimir resultados de la prueba de Kruskal-Wallis
print(kruskal_test4)
## $DMF
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Estrato
## Kruskal-Wallis chi-squared = 0.41703, df = 2, p-value = 0.8118
## 
## 
## $DSD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Estrato
## Kruskal-Wallis chi-squared = 0.78552, df = 2, p-value = 0.6752
## 
## 
## $CVD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Estrato
## Kruskal-Wallis chi-squared = 0.50473, df = 2, p-value = 0.777
## 
## 
## $FC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Estrato
## Kruskal-Wallis chi-squared = 0.63885, df = 2, p-value = 0.7266
## 
## 
## $IC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Estrato
## Kruskal-Wallis chi-squared = 6.2732, df = 2, p-value = 0.04343
# Imprimir resultados de la prueba de Kruskal-Wallis
print(kruskal_test5)
## $DMF
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Zona
## Kruskal-Wallis chi-squared = 47.238, df = 2, p-value = 5.526e-11
## 
## 
## $DSD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Zona
## Kruskal-Wallis chi-squared = 29.099, df = 2, p-value = 4.799e-07
## 
## 
## $CVD
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Zona
## Kruskal-Wallis chi-squared = 27.456, df = 2, p-value = 1.091e-06
## 
## 
## $FC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Zona
## Kruskal-Wallis chi-squared = 38.109, df = 2, p-value = 5.307e-09
## 
## 
## $IC
## 
##  Kruskal-Wallis rank sum test
## 
## data:  x by datos$Zona
## Kruskal-Wallis chi-squared = 27.273, df = 2, p-value = 1.196e-06

Pruebas Post Hoc

# Definir función para realizar la prueba de Wilcoxon-Mann-Whitney para comparaciones post hoc
wilcox_test_with_adjustment <- function(x, group) {
  pairwise.wilcox.test(x, group, p.adjust.method = "BH")
}

# Realizar prueba de Wilcoxon-Mann-Whitney para las diferentes variables categóricas
wilcox_test_comunidad <- lapply(datos_numericos, function(x) wilcox_test_with_adjustment(x, datos$Comunidad))
wilcox_test_sexo <- lapply(datos_numericos, function(x) wilcox_test_with_adjustment(x, datos$Sexo))
wilcox_test_edad <- lapply(datos_numericos, function(x) wilcox_test_with_adjustment(x, datos$Edad))
wilcox_test_estrato <- lapply(datos_numericos, function(x) wilcox_test_with_adjustment(x, datos$Estrato))
wilcox_test_zona <- lapply(datos_numericos, function(x) wilcox_test_with_adjustment(x, datos$Zona))

# Imprimir resultados de la prueba de Wilcoxon-Mann-Whitney
print(wilcox_test_comunidad)
## $DMF
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##            Chajana Huancasaya Japo    Koricancha Los Andes Mallcunuta Mecani 
## Huancasaya 0.66727 -          -       -          -         -          -      
## Japo       0.74378 0.52109    -       -          -         -          -      
## Koricancha 0.43881 0.61042    0.27636 -          -         -          -      
## Los Andes  0.00048 0.00019    0.00163 3.6e-05    -         -          -      
## Mallcunuta 0.01892 0.00651    0.04438 0.00151    0.20455   -          -      
## Mecani     0.00163 0.00445    0.00062 0.01921    1.3e-10   3.6e-08    -      
## Tomapirhua 0.07549 0.04746    0.14212 0.01426    0.10525   0.64471    1.3e-06
## Umabamba   0.01426 0.04067    0.00651 0.12668    1.1e-08   1.5e-06    0.48874
##            Tomapirhua
## Huancasaya -         
## Japo       -         
## Koricancha -         
## Los Andes  -         
## Mallcunuta -         
## Mecani     -         
## Tomapirhua -         
## Umabamba   6.0e-05   
## 
## P value adjustment method: BH 
## 
## $DSD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##            Chajana Huancasaya Japo    Koricancha Los Andes Mallcunuta Mecani
## Huancasaya 0.1384  -          -       -          -         -          -     
## Japo       0.7897  0.1854     -       -          -         -          -     
## Koricancha 0.5649  0.3589     0.6965  -          -         -          -     
## Los Andes  8.6e-09 1.3e-05    2.3e-09 1.2e-07    -         -          -     
## Mallcunuta 0.0167  0.3746     0.0192  0.0812     0.0003    -          -     
## Mecani     0.3502  0.0053     0.1733  0.0916     2.9e-12   9.6e-05    -     
## Tomapirhua 0.0823  0.7530     0.1102  0.2341     5.5e-05   0.5785     0.0022
## Umabamba   0.8463  0.0610     0.6419  0.3746     1.6e-10   0.0026     0.3828
##            Tomapirhua
## Huancasaya -         
## Japo       -         
## Koricancha -         
## Los Andes  -         
## Mallcunuta -         
## Mecani     -         
## Tomapirhua -         
## Umabamba   0.0359    
## 
## P value adjustment method: BH 
## 
## $CVD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##            Chajana Huancasaya Japo    Koricancha Los Andes Mallcunuta Mecani 
## Huancasaya 0.00286 -          -       -          -         -          -      
## Japo       0.96705 0.00180    -       -          -         -          -      
## Koricancha 0.01705 0.45339    0.01294 -          -         -          -      
## Los Andes  1.4e-06 0.08914    1.1e-06 0.01197    -         -          -      
## Mallcunuta 0.35339 0.04052    0.35339 0.21665    0.00022   -          -      
## Mecani     0.02161 0.35339    0.01970 0.84781    0.01008   0.27024    -      
## Tomapirhua 0.55309 0.01294    0.51209 0.09208    3.3e-05   0.73120    0.12828
## Umabamba   0.01077 0.51799    0.00954 0.92665    0.01294   0.14244    0.73120
##            Tomapirhua
## Huancasaya -         
## Japo       -         
## Koricancha -         
## Los Andes  -         
## Mallcunuta -         
## Mecani     -         
## Tomapirhua -         
## Umabamba   0.05818   
## 
## P value adjustment method: BH 
## 
## $FC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##            Chajana Huancasaya Japo    Koricancha Los Andes Mallcunuta Mecani 
## Huancasaya 0.73181 -          -       -          -         -          -      
## Japo       0.69409 0.98031    -       -          -         -          -      
## Koricancha 0.73181 0.49461    0.51119 -          -         -          -      
## Los Andes  6.2e-06 3.3e-05    3.3e-05 2.8e-06    -         -          -      
## Mallcunuta 0.00486 0.01628    0.01703 0.00157    0.05336   -          -      
## Mecani     0.02349 0.00823    0.00823 0.04794    2.1e-11   1.3e-07    -      
## Tomapirhua 0.07970 0.17875    0.16178 0.04702    0.00891   0.37310    5.0e-05
## Umabamba   0.09459 0.04684    0.04684 0.16178    1.1e-09   6.7e-06    0.61458
##            Tomapirhua
## Huancasaya -         
## Japo       -         
## Koricancha -         
## Los Andes  -         
## Mallcunuta -         
## Mecani     -         
## Tomapirhua -         
## Umabamba   0.00076   
## 
## P value adjustment method: BH 
## 
## $IC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##            Chajana Huancasaya Japo    Koricancha Los Andes Mallcunuta Mecani 
## Huancasaya 0.21390 -          -       -          -         -          -      
## Japo       0.03764 0.00104    -       -          -         -          -      
## Koricancha 0.08805 0.70452    0.00010 -          -         -          -      
## Los Andes  0.00909 0.23252    8.5e-07 0.37974    -         -          -      
## Mallcunuta 0.08805 0.00534    0.81117 0.00081    2.6e-05   -          -      
## Mecani     0.74373 0.31912    0.02620 0.19632    0.02620   0.06502    -      
## Tomapirhua 0.47195 0.06502    0.19632 0.01637    0.00081   0.28642    0.36299
## Umabamba   0.48803 0.55660    0.00534 0.30946    0.04950   0.01688    0.68806
##            Tomapirhua
## Huancasaya -         
## Japo       -         
## Koricancha -         
## Los Andes  -         
## Mallcunuta -         
## Mecani     -         
## Tomapirhua -         
## Umabamba   0.17013   
## 
## P value adjustment method: BH
print(wilcox_test_sexo)
## $DMF
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Hembra 
## Macho 8.3e-07
## 
## P value adjustment method: BH 
## 
## $DSD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Hembra
## Macho 0.02  
## 
## P value adjustment method: BH 
## 
## $CVD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Hembra
## Macho 0.0022
## 
## P value adjustment method: BH 
## 
## $FC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Hembra 
## Macho 1.4e-05
## 
## P value adjustment method: BH 
## 
## $IC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Hembra
## Macho 0.0051
## 
## P value adjustment method: BH
print(wilcox_test_edad)
## $DMF
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##   A       B       C     
## B < 2e-16 -       -     
## C < 2e-16 5.3e-16 -     
## D < 2e-16 < 2e-16 0.0028
## 
## P value adjustment method: BH 
## 
## $DSD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##   A       B       C   
## B 4.3e-10 -       -   
## C < 2e-16 1.1e-08 -   
## D < 2e-16 6.6e-11 0.38
## 
## P value adjustment method: BH 
## 
## $CVD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##   A       B       C      
## B 0.03509 -       -      
## C 0.00026 0.12619 -      
## D 1.4e-08 0.00061 0.03509
## 
## P value adjustment method: BH 
## 
## $FC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##   A       B       C     
## B < 2e-16 -       -     
## C < 2e-16 2.8e-14 -     
## D < 2e-16 < 2e-16 0.0071
## 
## P value adjustment method: BH 
## 
## $IC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##   A       B       C    
## B 8.2e-06 -       -    
## C 5.5e-15 0.001   -    
## D < 2e-16 5.2e-05 0.393
## 
## P value adjustment method: BH
print(wilcox_test_estrato)
## $DMF
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Alto Bajo
## Bajo  0.78 -   
## Medio 0.78 0.78
## 
## P value adjustment method: BH 
## 
## $DSD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Alto Bajo
## Bajo  0.71 -   
## Medio 0.71 0.71
## 
## P value adjustment method: BH 
## 
## $CVD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Alto Bajo
## Bajo  0.96 -   
## Medio 0.89 0.89
## 
## P value adjustment method: BH 
## 
## $FC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Alto Bajo
## Bajo  0.71 -   
## Medio 0.71 0.71
## 
## P value adjustment method: BH 
## 
## $IC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Alto  Bajo 
## Bajo  0.241 -    
## Medio 0.038 0.320
## 
## P value adjustment method: BH
print(wilcox_test_zona)
## $DMF
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Centro  Norte  
## Norte 0.24    -      
## Sur   7.8e-10 7.5e-08
## 
## P value adjustment method: BH 
## 
## $DSD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Centro  Norte  
## Norte 0.00045 -      
## Sur   4.5e-07 0.08242
## 
## P value adjustment method: BH 
## 
## $CVD
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Centro  Norte  
## Norte 1.2e-05 -      
## Sur   0.95    1.2e-05
## 
## P value adjustment method: BH 
## 
## $FC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Centro  Norte  
## Norte 0.071   -      
## Sur   8.9e-09 2.1e-05
## 
## P value adjustment method: BH 
## 
## $IC
## 
##  Pairwise comparisons using Wilcoxon rank sum test with continuity correction 
## 
## data:  x and group 
## 
##       Centro  Norte  
## Norte 2.2e-06 -      
## Sur   0.37048 0.00012
## 
## P value adjustment method: BH

Conclusiones

  • El promedio de finura de fibra del distrito de Cojata es de 20.46 micras, encontrándose en la calidad “Baby alpaca”, conforme a las normas técnicas peruanas de clasificado de fibra vigentes.
  • El factor edad, sexo, comunidad y zona de crianza, influyen sobre el promedio de las características físicas de la fibra.
  • Las correlaciones entre DMF y DSD (0.77) y DMF con FC (-0.87) son favorables para seleccionar alpacas para estas 3 características de fibra.