library(readxl)
library(outliers)
datos = read_excel("//cloud//project//pesofrescopa.xlsx", sheet = 1)
tratamiento<- as.factor(datos$tratamiento)
bloque<- as.factor(datos$bloque)
sujeto<- as.factor(datos$sujeto)
dca1<-aov(datos$pesofresco~tratamiento+bloque+Error(sujeto))
dca1
##
## Call:
## aov(formula = datos$pesofresco ~ tratamiento + bloque + Error(sujeto))
##
## Grand Mean: 2.8675
##
## Stratum 1: sujeto
##
## Terms:
## tratamiento bloque Residuals
## Sum of Squares 26.184900 1.288225 0.445275
## Deg. of Freedom 3 1 3
##
## Residual standard error: 0.3852597
## Estimated effects may be unbalanced
##
## Stratum 2: Within
##
## Terms:
## Residuals
## Sum of Squares 2.6123
## Deg. of Freedom 8
##
## Residual standard error: 0.5714346
summary(dca1)
##
## Error: sujeto
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 26.185 8.728 58.806 0.00365 **
## bloque 1 1.288 1.288 8.679 0.06022 .
## Residuals 3 0.445 0.148
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Error: Within
## Df Sum Sq Mean Sq F value Pr(>F)
## Residuals 8 2.612 0.3265
x <-dca1$sujeto$residuals
y <-dca1$Within$residuals
sc.error.a <-sum(x^2) #SUMA DE CUADRADOS DEL ERROR EXPERIMENTAL
sc.error.b <-sum(y^2) #SUMA DE CUADRADOS DEL ERROR MUESTRAL
format(x, big.mark = ",")
## 2 3 4 5 6
## "-0.237500000" "-0.313212521" " 0.442949395" " 0.194480076" "-0.238188476"
## 7 8
## "-0.001636634" " 0.001889822"
dca2<-aov(datos$pesofresco~tratamiento+bloque+sujeto%in%bloque%in%tratamiento)
summary(dca2)
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 26.185 8.728 26.730 0.00016 ***
## bloque 1 1.288 1.288 3.945 0.08225 .
## tratamiento:bloque:sujeto 3 0.445 0.148 0.455 0.72132
## Residuals 8 2.612 0.327
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
mod1 = aov(datos$pesofresco ~ tratamiento*bloque, datos)
sum1<-summary(mod1)
sum1 <- unlist(sum1)
sum1 = sum1[9]
summary(mod1)
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 26.185 8.728 26.730 0.00016 ***
## bloque 1 1.288 1.288 3.945 0.08225 .
## tratamiento:bloque 3 0.445 0.148 0.455 0.72132
## Residuals 8 2.612 0.327
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
TukeyHSD(mod1, "tratamiento")
## Warning in replications(paste("~", xx), data = mf): non-factors ignored: bloque
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## tratamiento, bloque
## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = datos$pesofresco ~ tratamiento * bloque, data = datos)
##
## $tratamiento
## diff lwr upr p adj
## T2-T1 -2.825 -4.1189593 -1.5310407 0.0005184
## T3-T1 -3.165 -4.4589593 -1.8710407 0.0002338
## T4-T1 -2.820 -4.1139593 -1.5260407 0.0005247
## T3-T2 -0.340 -1.6339593 0.9539593 0.8336662
## T4-T2 0.005 -1.2889593 1.2989593 0.9999993
## T4-T3 0.345 -0.9489593 1.6389593 0.8278266
library(agricolae)
duncan.test(mod1, 'tratamiento', console = T)
##
## Study: mod1 ~ "tratamiento"
##
## Duncan's new multiple range test
## for datos$pesofresco
##
## Mean Square Error: 0.3265375
##
## tratamiento, means
##
## datos.pesofresco std r se Min Max Q25 Q50 Q75
## T1 5.070 0.7841343 4 0.2857173 4.18 5.82 4.5325 5.140 5.6775
## T2 2.245 0.7001190 4 0.2857173 1.63 3.14 1.7200 2.105 2.6300
## T3 1.905 0.4403408 4 0.2857173 1.27 2.28 1.8100 2.035 2.1300
## T4 2.250 0.3868678 4 0.2857173 1.81 2.73 2.0425 2.230 2.4375
##
## Alpha: 0.05 ; DF Error: 8
##
## Critical Range
## 2 3 4
## 0.9317762 0.9709988 0.9929221
##
## Means with the same letter are not significantly different.
##
## datos$pesofresco groups
## T1 5.070 a
## T4 2.250 b
## T2 2.245 b
## T3 1.905 b
muestreo 2
library(readxl)
library(outliers)
datos = read_excel("//cloud//project//pesofrescopa2.xlsx", sheet = 1)
tratamiento<- as.factor(datos$tratamiento)
bloque<- as.factor(datos$bloque)
sujeto<- as.factor(datos$sujeto)
dca2<-aov(datos$pesofresco2~tratamiento+bloque+Error(sujeto))
dca2
##
## Call:
## aov(formula = datos$pesofresco2 ~ tratamiento + bloque + Error(sujeto))
##
## Grand Mean: 3.498125
##
## Stratum 1: sujeto
##
## Terms:
## tratamiento bloque Residuals
## Sum of Squares 42.10867 0.07426 1.73647
## Deg. of Freedom 3 1 3
##
## Residual standard error: 0.7608041
## Estimated effects may be unbalanced
##
## Stratum 2: Within
##
## Terms:
## Residuals
## Sum of Squares 5.60625
## Deg. of Freedom 8
##
## Residual standard error: 0.8371268
summary(dca2)
##
## Error: sujeto
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 42.11 14.036 24.250 0.0132 *
## bloque 1 0.07 0.074 0.128 0.7439
## Residuals 3 1.74 0.579
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Error: Within
## Df Sum Sq Mean Sq F value Pr(>F)
## Residuals 8 5.606 0.7008
x <-dca2$sujeto$residuals
y <-dca2$Within$residuals
sc.error.a <-sum(x^2) #SUMA DE CUADRADOS DEL ERROR EXPERIMENTAL
sc.error.b <-sum(y^2) #SUMA DE CUADRADOS DEL ERROR MUESTRAL
format(x, big.mark = ",")
## 2 3 4 5 6 7
## "-0.0337500" "-0.1133050" " 0.1602375" " 0.6316650" "-0.7736284" "-0.5474541"
## 8
## " 0.6321456"
dca3<-aov(datos$pesofresco2~tratamiento+bloque+sujeto%in%bloque%in%tratamiento)
summary(dca3)
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 42.11 14.036 20.029 0.000446 ***
## bloque 1 0.07 0.074 0.106 0.753140
## tratamiento:bloque:sujeto 3 1.74 0.579 0.826 0.515609
## Residuals 8 5.61 0.701
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
mod2 = aov(datos$pesofresco2 ~ tratamiento*bloque, datos)
sum2<-summary(mod1)
sum2 <- unlist(sum1)
sum2 = sum1[9]
summary(mod2)
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 42.11 14.036 20.029 0.000446 ***
## bloque 1 0.07 0.074 0.106 0.753140
## tratamiento:bloque 3 1.74 0.579 0.826 0.515609
## Residuals 8 5.61 0.701
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
TukeyHSD(mod2, "tratamiento")
## Warning in replications(paste("~", xx), data = mf): non-factors ignored: bloque
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## tratamiento, bloque
## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = datos$pesofresco2 ~ tratamiento * bloque, data = datos)
##
## $tratamiento
## diff lwr upr p adj
## T2-T1 -4.2950 -6.1905939 -2.399406 0.0004007
## T3-T1 -3.2275 -5.1230939 -1.331906 0.0026986
## T4-T1 -3.3450 -5.2405939 -1.449406 0.0021477
## T3-T2 1.0675 -0.8280939 2.963094 0.3382784
## T4-T2 0.9500 -0.9455939 2.845594 0.4275581
## T4-T3 -0.1175 -2.0130939 1.778094 0.9969979
library(agricolae)
duncan.test(mod2, 'tratamiento', console = T)
##
## Study: mod2 ~ "tratamiento"
##
## Duncan's new multiple range test
## for datos$pesofresco2
##
## Mean Square Error: 0.7007813
##
## tratamiento, means
##
## datos.pesofresco2 std r se Min Max Q25 Q50 Q75
## T1 6.2150 1.1816514 4 0.4185634 5.10 7.50 5.2725 6.130 7.0725
## T2 1.9200 0.1293574 4 0.4185634 1.81 2.08 1.8175 1.895 1.9975
## T3 2.9875 0.7403321 4 0.4185634 2.10 3.83 2.5800 3.010 3.4175
## T4 2.8700 0.7149825 4 0.4185634 2.25 3.89 2.4750 2.670 3.0650
##
## Alpha: 0.05 ; DF Error: 8
##
## Critical Range
## 2 3 4
## 1.365012 1.422471 1.454588
##
## Means with the same letter are not significantly different.
##
## datos$pesofresco2 groups
## T1 6.2150 a
## T3 2.9875 b
## T4 2.8700 b
## T2 1.9200 b
Muestreo 3
library(readxl)
library(outliers)
datos = read_excel("//cloud//project//pesofrescopa2.xlsx", sheet = 1)
tratamiento<- as.factor(datos$tratamiento)
bloque<- as.factor(datos$bloque)
sujeto<- as.factor(datos$sujeto)
dca2<-aov(datos$pesofresco2~tratamiento+bloque+Error(sujeto))
dca2
##
## Call:
## aov(formula = datos$pesofresco2 ~ tratamiento + bloque + Error(sujeto))
##
## Grand Mean: 3.498125
##
## Stratum 1: sujeto
##
## Terms:
## tratamiento bloque Residuals
## Sum of Squares 42.10867 0.07426 1.73647
## Deg. of Freedom 3 1 3
##
## Residual standard error: 0.7608041
## Estimated effects may be unbalanced
##
## Stratum 2: Within
##
## Terms:
## Residuals
## Sum of Squares 5.60625
## Deg. of Freedom 8
##
## Residual standard error: 0.8371268
summary(dca2)
##
## Error: sujeto
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 42.11 14.036 24.250 0.0132 *
## bloque 1 0.07 0.074 0.128 0.7439
## Residuals 3 1.74 0.579
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Error: Within
## Df Sum Sq Mean Sq F value Pr(>F)
## Residuals 8 5.606 0.7008
x <-dca2$sujeto$residuals
y <-dca2$Within$residuals
sc.error.a <-sum(x^2) #SUMA DE CUADRADOS DEL ERROR EXPERIMENTAL
sc.error.b <-sum(y^2) #SUMA DE CUADRADOS DEL ERROR MUESTRAL
format(x, big.mark = ",")
## 2 3 4 5 6 7
## "-0.0337500" "-0.1133050" " 0.1602375" " 0.6316650" "-0.7736284" "-0.5474541"
## 8
## " 0.6321456"
dca3<-aov(datos$pesofresco2~tratamiento+bloque+sujeto%in%bloque%in%tratamiento)
summary(dca3)
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 42.11 14.036 20.029 0.000446 ***
## bloque 1 0.07 0.074 0.106 0.753140
## tratamiento:bloque:sujeto 3 1.74 0.579 0.826 0.515609
## Residuals 8 5.61 0.701
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
mod2 = aov(datos$pesofresco2 ~ tratamiento*bloque, datos)
sum2<-summary(mod1)
sum2 <- unlist(sum1)
sum2 = sum1[9]
summary(mod2)
## Df Sum Sq Mean Sq F value Pr(>F)
## tratamiento 3 42.11 14.036 20.029 0.000446 ***
## bloque 1 0.07 0.074 0.106 0.753140
## tratamiento:bloque 3 1.74 0.579 0.826 0.515609
## Residuals 8 5.61 0.701
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
TukeyHSD(mod2, "tratamiento")
## Warning in replications(paste("~", xx), data = mf): non-factors ignored: bloque
## Warning in replications(paste("~", xx), data = mf): non-factors ignored:
## tratamiento, bloque
## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = datos$pesofresco2 ~ tratamiento * bloque, data = datos)
##
## $tratamiento
## diff lwr upr p adj
## T2-T1 -4.2950 -6.1905939 -2.399406 0.0004007
## T3-T1 -3.2275 -5.1230939 -1.331906 0.0026986
## T4-T1 -3.3450 -5.2405939 -1.449406 0.0021477
## T3-T2 1.0675 -0.8280939 2.963094 0.3382784
## T4-T2 0.9500 -0.9455939 2.845594 0.4275581
## T4-T3 -0.1175 -2.0130939 1.778094 0.9969979
library(agricolae)
duncan.test(mod2, 'tratamiento', console = T)
##
## Study: mod2 ~ "tratamiento"
##
## Duncan's new multiple range test
## for datos$pesofresco2
##
## Mean Square Error: 0.7007813
##
## tratamiento, means
##
## datos.pesofresco2 std r se Min Max Q25 Q50 Q75
## T1 6.2150 1.1816514 4 0.4185634 5.10 7.50 5.2725 6.130 7.0725
## T2 1.9200 0.1293574 4 0.4185634 1.81 2.08 1.8175 1.895 1.9975
## T3 2.9875 0.7403321 4 0.4185634 2.10 3.83 2.5800 3.010 3.4175
## T4 2.8700 0.7149825 4 0.4185634 2.25 3.89 2.4750 2.670 3.0650
##
## Alpha: 0.05 ; DF Error: 8
##
## Critical Range
## 2 3 4
## 1.365012 1.422471 1.454588
##
## Means with the same letter are not significantly different.
##
## datos$pesofresco2 groups
## T1 6.2150 a
## T3 2.9875 b
## T4 2.8700 b
## T2 1.9200 b