DisenoMaiz <- read.csv("~/Desktop/DisenoMaiz.csv")
View(DisenoMaiz)
DisenoMaiz$t<-as.factor(DisenoMaiz$t)
DisenoMaiz$D<-as.factor(DisenoMaiz$D)
DisenoMaiz$C<-as.factor(DisenoMaiz$C)
#ANOVA
Polifenoles<-aov(Abs~t*D*C, data = DisenoMaiz)
anova(Polifenoles)
## Analysis of Variance Table
##
## Response: Abs
## Df Sum Sq Mean Sq F value Pr(>F)
## t 1 0.62146 0.62146 89.0700 6.107e-08 ***
## D 1 0.02007 0.02007 2.8762 0.10926
## C 1 0.24241 0.24241 34.7425 2.264e-05 ***
## t:D 1 0.00331 0.00331 0.4749 0.50061
## t:C 1 0.03745 0.03745 5.3669 0.03411 *
## D:C 1 0.00045 0.00045 0.0646 0.80262
## t:D:C 1 0.01664 0.01664 2.3853 0.14203
## Residuals 16 0.11164 0.00698
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Hipotesis
#Ho=todas las medias son iguales
#Ha=al menos es diferente, hay influencia de algún factor
#alfa = 0.05
#Conclusión (Pr(F)>0.05) = Que si hay efecto de la interacción
#COMPROBACION DE SUPUESTOS
#Normalidad
#Gráfica
ResiduosPoli<-resid(Polifenoles)
qqnorm(ResiduosPoli)
plot(density(residuals(Polifenoles)))
#Analitica
library(MASS)
RESIDUALESPoli<-studres(Polifenoles)
shapiro.test(RESIDUALESPoli)
##
## Shapiro-Wilk normality test
##
## data: RESIDUALESPoli
## W = 0.90823, p-value = 0.03229
#Homogeneidad de varianza
#Gráfica
estimadosPOLI<-fitted(Polifenoles)
plot(estimadosPOLI,ResiduosPoli,main="tratamiento en maiz", xlab="Tratamiento", ylab="Residuos")
#Analitica
library(car)
## Loading required package: carData
#Prueba de Leven
leveneTest(Abs~t*D*C, data = DisenoMaiz)
## Levene's Test for Homogeneity of Variance (center = median)
## Df F value Pr(>F)
## group 7 0.3558 0.9148
## 16
#Ho: todas las varianzas son iguales
#Ha: al menos una varianza es diferente
#alfa = 0.05
#Conclusión: se cumple con el supuesto de homogeneidad de varianza
#Todos los gráficos
plot(Polifenoles)
#DETERMINACIÓN DE MEJOR TRATAMIENTO
library(agricolae)
#DMS de Turkey
Compat<-HSD.test(Polifenoles,"t",group=TRUE)
Compat
## $statistics
## MSerror Df Mean CV MSD
## 0.006977208 16 0.46325 18.03123 0.07229057
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey t 2 2.997999 0.05
##
## $means
## Abs std r Min Max Q25 Q50 Q75
## 1 0.3023333 0.09452785 12 0.175 0.474 0.25125 0.2970 0.32175
## 2 0.6241667 0.17416598 12 0.349 0.869 0.48350 0.5795 0.79925
##
## $comparison
## NULL
##
## $groups
## Abs groups
## 2 0.6241667 a
## 1 0.3023333 b
##
## attr(,"class")
## [1] "group"
CompaC<-HSD.test(Polifenoles,"C",group=TRUE)
CompaC
## $statistics
## MSerror Df Mean CV MSD
## 0.006977208 16 0.46325 18.03123 0.07229057
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey C 2 2.997999 0.05
##
## $means
## Abs std r Min Max Q25 Q50 Q75
## 1 0.36275 0.1431878 12 0.175 0.583 0.25125 0.3335 0.47650
## 2 0.56375 0.2307077 12 0.281 0.869 0.32825 0.5250 0.79925
##
## $comparison
## NULL
##
## $groups
## Abs groups
## 2 0.56375 a
## 1 0.36275 b
##
## attr(,"class")
## [1] "group"
CompaD<-HSD.test(Polifenoles,"D",group=TRUE)
CompaD
## $statistics
## MSerror Df Mean CV MSD
## 0.006977208 16 0.46325 18.03123 0.07229057
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey D 2 2.997999 0.05
##
## $means
## Abs std r Min Max Q25 Q50 Q75
## 1 0.4343333 0.2288554 12 0.181 0.869 0.27550 0.3315 0.53375
## 2 0.4921667 0.2038787 12 0.175 0.849 0.32925 0.4725 0.57775
##
## $comparison
## NULL
##
## $groups
## Abs groups
## 2 0.4921667 a
## 1 0.4343333 a
##
## attr(,"class")
## [1] "group"
CompatD<-HSD.test(Polifenoles,c("t","D"), group=TRUE)
CompatD
## $statistics
## MSerror Df Mean CV MSD
## 0.006977208 16 0.46325 18.03123 0.1379752
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey t:D 4 4.046093 0.05
##
## $means
## Abs std r Min Max Q25 Q50 Q75
## 1:1 0.2616667 0.05062674 6 0.181 0.314 0.23575 0.2700 0.3005
## 1:2 0.3430000 0.11456876 6 0.175 0.474 0.29475 0.3255 0.4365
## 2:1 0.6070000 0.20275207 6 0.349 0.869 0.47650 0.5805 0.7610
## 2:2 0.6413333 0.15785647 6 0.468 0.849 0.55275 0.5795 0.7660
##
## $comparison
## NULL
##
## $groups
## Abs groups
## 2:2 0.6413333 a
## 2:1 0.6070000 a
## 1:2 0.3430000 b
## 1:1 0.2616667 b
##
## attr(,"class")
## [1] "group"
CompatC<-HSD.test(Polifenoles, c("t","D"),group=TRUE)
CompatC
## $statistics
## MSerror Df Mean CV MSD
## 0.006977208 16 0.46325 18.03123 0.1379752
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey t:D 4 4.046093 0.05
##
## $means
## Abs std r Min Max Q25 Q50 Q75
## 1:1 0.2616667 0.05062674 6 0.181 0.314 0.23575 0.2700 0.3005
## 1:2 0.3430000 0.11456876 6 0.175 0.474 0.29475 0.3255 0.4365
## 2:1 0.6070000 0.20275207 6 0.349 0.869 0.47650 0.5805 0.7610
## 2:2 0.6413333 0.15785647 6 0.468 0.849 0.55275 0.5795 0.7660
##
## $comparison
## NULL
##
## $groups
## Abs groups
## 2:2 0.6413333 a
## 2:1 0.6070000 a
## 1:2 0.3430000 b
## 1:1 0.2616667 b
##
## attr(,"class")
## [1] "group"
CompaDC<-HSD.test(Polifenoles, c("D","C"),group=TRUE)
CompaDC
## $statistics
## MSerror Df Mean CV MSD
## 0.006977208 16 0.46325 18.03123 0.1379752
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey D:C 4 4.046093 0.05
##
## $means
## Abs std r Min Max Q25 Q50 Q75
## 1:1 0.3295000 0.1289213 6 0.181 0.487 0.23575 0.304 0.44200
## 1:2 0.5391667 0.2687522 6 0.281 0.869 0.30875 0.494 0.76100
## 2:1 0.3960000 0.1607234 6 0.175 0.583 0.29475 0.393 0.52575
## 2:2 0.5883333 0.2083724 6 0.333 0.849 0.47175 0.525 0.76425
##
## $comparison
## NULL
##
## $groups
## Abs groups
## 2:2 0.5883333 a
## 1:2 0.5391667 a
## 2:1 0.3960000 b
## 1:1 0.3295000 b
##
## attr(,"class")
## [1] "group"
CompatDC<-HSD.test(Polifenoles, c("D","t", "C"),group=TRUE)
CompatDC
## $statistics
## MSerror Df Mean CV MSD
## 0.006977208 16 0.46325 18.03123 0.2361246
##
## $parameters
## test name.t ntr StudentizedRange alpha
## Tukey D:t:C 8 4.89622 0.05
##
## $means
## Abs std r Min Max Q25 Q50 Q75
## 1:1:1 0.2226667 0.03927255 3 0.181 0.259 0.2045 0.228 0.2435
## 1:1:2 0.3006667 0.01738774 3 0.281 0.314 0.2940 0.307 0.3105
## 1:2:1 0.4363333 0.07595613 3 0.349 0.487 0.4110 0.473 0.4800
## 1:2:2 0.7776667 0.09808330 3 0.674 0.869 0.7320 0.790 0.8295
## 2:1:1 0.2600000 0.07522633 3 0.175 0.318 0.2310 0.287 0.3025
## 2:1:2 0.4260000 0.08055433 3 0.333 0.474 0.4020 0.471 0.4725
## 2:2:1 0.5320000 0.05859181 3 0.468 0.583 0.5065 0.545 0.5640
## 2:2:2 0.7506667 0.15166520 3 0.576 0.849 0.7015 0.827 0.8380
##
## $comparison
## NULL
##
## $groups
## Abs groups
## 1:2:2 0.7776667 a
## 2:2:2 0.7506667 ab
## 2:2:1 0.5320000 bc
## 1:2:1 0.4363333 cd
## 2:1:2 0.4260000 cd
## 1:1:2 0.3006667 cd
## 2:1:1 0.2600000 d
## 1:1:1 0.2226667 d
##
## attr(,"class")
## [1] "group"
#El mejor tratamiento es el 1:2:2 ya que produce más concentración de polifenoles
#Gráficos
library(tidyverse)
## ── Attaching packages
## ───────────────────────────────────────
## tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6 ✔ purrr 1.0.1
## ✔ tibble 3.1.7 ✔ dplyr 1.1.0
## ✔ tidyr 1.2.0 ✔ stringr 1.4.0
## ✔ readr 2.1.2 ✔ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ dplyr::recode() masks car::recode()
## ✖ dplyr::select() masks MASS::select()
## ✖ purrr::some() masks car::some()
library(pastecs)
##
## Attaching package: 'pastecs'
##
## The following objects are masked from 'package:dplyr':
##
## first, last
##
## The following object is masked from 'package:tidyr':
##
## extract
stat.desc(DisenoMaiz, norm = TRUE)
## Tratamiento Repet t D C Abs
## nbr.val 24.0000000 24.0000000000 NA NA NA 24.00000000
## nbr.null 0.0000000 0.0000000000 NA NA NA 0.00000000
## nbr.na 0.0000000 0.0000000000 NA NA NA 0.00000000
## min 1.0000000 1.0000000000 NA NA NA 0.17500000
## max 8.0000000 3.0000000000 NA NA NA 0.86900000
## range 7.0000000 2.0000000000 NA NA NA 0.69400000
## sum 108.0000000 48.0000000000 NA NA NA 11.11800000
## median 4.5000000 2.0000000000 NA NA NA 0.46950000
## mean 4.5000000 2.0000000000 NA NA NA 0.46325000
## SE.mean 0.4777665 0.1702513062 NA NA NA 0.04368494
## CI.mean.0.95 0.9883354 0.3521916602 NA NA NA 0.09036919
## var 5.4782609 0.6956521739 NA NA NA 0.04580098
## std.dev 2.3405685 0.8340576562 NA NA NA 0.21401163
## coef.var 0.5201263 0.4170288281 NA NA NA 0.46197870
## skewness 0.0000000 0.0000000000 NA NA NA 0.53934917
## skew.2SE 0.0000000 0.0000000000 NA NA NA 0.57102889
## kurtosis -1.3818618 -1.6223958333 NA NA NA -0.96100190
## kurt.2SE -0.7528308 -0.8838724915 NA NA NA -0.52354865
## normtest.W 0.9321614 0.7972722576 NA NA NA 0.91726440
## normtest.p 0.1089638 0.0002659244 NA NA NA 0.05083304
#Conclusión cumple con la normalidad