Evaluacion- Computacion
Paola Andrea Ospina S
12/5/2022
set.seed(1007355141)
coords<-expand.grid(x=1:10,
y=1:12)
CBD<-c(rnorm(30,60,2),
rnorm(30,50,1.5),
runif(30,30,40),
rnorm(30,40,3));CBD## [1] 58.78956 59.93965 60.10029 62.59060 59.98009 62.13517 57.34465 61.64193
## [9] 57.68583 58.98804 61.12674 59.37396 61.28387 57.72517 58.17340 57.44321
## [17] 61.72839 58.83681 59.99402 59.88482 61.34530 57.50246 64.15116 59.12774
## [25] 60.50127 54.61255 61.98738 58.65168 59.20183 56.63738 50.54898 52.75790
## [33] 46.60616 47.71437 49.23800 51.62073 50.83690 53.28721 48.71915 50.33189
## [41] 51.00709 50.59940 46.64245 50.23388 46.63812 49.98414 49.04254 48.92180
## [49] 52.00325 49.59966 51.23691 50.51886 50.76543 48.69077 46.94054 50.24352
## [57] 49.63330 49.91494 49.41885 49.20905 36.85008 37.82991 35.71252 39.71607
## [65] 33.89718 34.43725 38.96448 31.11166 32.65631 31.03818 38.99152 33.42717
## [73] 37.12643 31.84185 35.48942 33.46442 37.64634 39.53842 37.21001 38.97064
## [81] 38.00847 34.19722 32.81589 32.78877 37.43241 34.38809 35.54387 31.11546
## [89] 36.51418 32.53683 39.92675 35.94137 44.25427 45.75735 45.22681 37.26986
## [97] 36.19437 38.08939 43.78280 43.28802 40.31099 38.71304 39.96264 33.51157
## [105] 39.24624 42.83866 37.91353 40.69080 40.13765 41.34808 40.76795 40.84164
## [113] 41.50470 41.35002 39.30585 39.49688 40.62470 38.57651 41.13862 38.00354Accesion<-gl(4,30,120, labels=c("A1","A2","A3","A4"))
df<-data.frame(x=coords$x, y=coords$y, CBD=CBD,
Accesion=Accesion); df## x y CBD Accesion
## 1 1 1 58.78956 A1
## 2 2 1 59.93965 A1
## 3 3 1 60.10029 A1
## 4 4 1 62.59060 A1
## 5 5 1 59.98009 A1
## 6 6 1 62.13517 A1
## 7 7 1 57.34465 A1
## 8 8 1 61.64193 A1
## 9 9 1 57.68583 A1
## 10 10 1 58.98804 A1
## 11 1 2 61.12674 A1
## 12 2 2 59.37396 A1
## 13 3 2 61.28387 A1
## 14 4 2 57.72517 A1
## 15 5 2 58.17340 A1
## 16 6 2 57.44321 A1
## 17 7 2 61.72839 A1
## 18 8 2 58.83681 A1
## 19 9 2 59.99402 A1
## 20 10 2 59.88482 A1
## 21 1 3 61.34530 A1
## 22 2 3 57.50246 A1
## 23 3 3 64.15116 A1
## 24 4 3 59.12774 A1
## 25 5 3 60.50127 A1
## 26 6 3 54.61255 A1
## 27 7 3 61.98738 A1
## 28 8 3 58.65168 A1
## 29 9 3 59.20183 A1
## 30 10 3 56.63738 A1
## 31 1 4 50.54898 A2
## 32 2 4 52.75790 A2
## 33 3 4 46.60616 A2
## 34 4 4 47.71437 A2
## 35 5 4 49.23800 A2
## 36 6 4 51.62073 A2
## 37 7 4 50.83690 A2
## 38 8 4 53.28721 A2
## 39 9 4 48.71915 A2
## 40 10 4 50.33189 A2
## 41 1 5 51.00709 A2
## 42 2 5 50.59940 A2
## 43 3 5 46.64245 A2
## 44 4 5 50.23388 A2
## 45 5 5 46.63812 A2
## 46 6 5 49.98414 A2
## 47 7 5 49.04254 A2
## 48 8 5 48.92180 A2
## 49 9 5 52.00325 A2
## 50 10 5 49.59966 A2
## 51 1 6 51.23691 A2
## 52 2 6 50.51886 A2
## 53 3 6 50.76543 A2
## 54 4 6 48.69077 A2
## 55 5 6 46.94054 A2
## 56 6 6 50.24352 A2
## 57 7 6 49.63330 A2
## 58 8 6 49.91494 A2
## 59 9 6 49.41885 A2
## 60 10 6 49.20905 A2
## 61 1 7 36.85008 A3
## 62 2 7 37.82991 A3
## 63 3 7 35.71252 A3
## 64 4 7 39.71607 A3
## 65 5 7 33.89718 A3
## 66 6 7 34.43725 A3
## 67 7 7 38.96448 A3
## 68 8 7 31.11166 A3
## 69 9 7 32.65631 A3
## 70 10 7 31.03818 A3
## 71 1 8 38.99152 A3
## 72 2 8 33.42717 A3
## 73 3 8 37.12643 A3
## 74 4 8 31.84185 A3
## 75 5 8 35.48942 A3
## 76 6 8 33.46442 A3
## 77 7 8 37.64634 A3
## 78 8 8 39.53842 A3
## 79 9 8 37.21001 A3
## 80 10 8 38.97064 A3
## 81 1 9 38.00847 A3
## 82 2 9 34.19722 A3
## 83 3 9 32.81589 A3
## 84 4 9 32.78877 A3
## 85 5 9 37.43241 A3
## 86 6 9 34.38809 A3
## 87 7 9 35.54387 A3
## 88 8 9 31.11546 A3
## 89 9 9 36.51418 A3
## 90 10 9 32.53683 A3
## 91 1 10 39.92675 A4
## 92 2 10 35.94137 A4
## 93 3 10 44.25427 A4
## 94 4 10 45.75735 A4
## 95 5 10 45.22681 A4
## 96 6 10 37.26986 A4
## 97 7 10 36.19437 A4
## 98 8 10 38.08939 A4
## 99 9 10 43.78280 A4
## 100 10 10 43.28802 A4
## 101 1 11 40.31099 A4
## 102 2 11 38.71304 A4
## 103 3 11 39.96264 A4
## 104 4 11 33.51157 A4
## 105 5 11 39.24624 A4
## 106 6 11 42.83866 A4
## 107 7 11 37.91353 A4
## 108 8 11 40.69080 A4
## 109 9 11 40.13765 A4
## 110 10 11 41.34808 A4
## 111 1 12 40.76795 A4
## 112 2 12 40.84164 A4
## 113 3 12 41.50470 A4
## 114 4 12 41.35002 A4
## 115 5 12 39.30585 A4
## 116 6 12 39.49688 A4
## 117 7 12 40.62470 A4
## 118 8 12 38.57651 A4
## 119 9 12 41.13862 A4
## 120 10 12 38.00354 A4\[H_0: \mu_{A1}=\mu_{A2}=\mu_{A3}=\mu_{A4}\] \[H_a: at~least~one~is~different \] ## Estadistica descriptiva
ggplot(df)+
aes(Accesion,CBD,fill=Accesion)+
geom_boxplot()+
geom_hline(yintercept = 5.2) #linea horizontal
library(dplyr)## Warning: package 'dplyr' was built under R version 4.1.3##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniondf %>%
group_by(Accesion) %>%
summarise(media=mean(CBD),
desv=sd(CBD),
cv=100*desv/media)## # A tibble: 4 x 4
## Accesion media desv cv
## <fct> <dbl> <dbl> <dbl>
## 1 A1 59.6 2.04 3.41
## 2 A2 49.8 1.71 3.43
## 3 A3 35.4 2.73 7.73
## 4 A4 40.2 2.74 6.81Analisis de varianza
mod1=aov(CBD~Accesion,data=df)
s_mod1=summary(mod1)
p_valor=s_mod1[[1]][1,5]
ifelse(p_valor<0.05,"Rechazo H0", "No rechazo H0")## [1] "Rechazo H0"prueba de Tukey-comparacion de medias
TukeyHSD(mod1,"Accesion")## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = CBD ~ Accesion, data = df)
##
## $Accesion
## diff lwr upr p adj
## A2-A1 -9.852638 -11.431888 -8.273389 0
## A3-A1 -24.240797 -25.820046 -22.661547 0
## A4-A1 -19.415678 -20.994928 -17.836428 0
## A3-A2 -14.388158 -15.967408 -12.808908 0
## A4-A2 -9.563039 -11.142289 -7.983790 0
## A4-A3 4.825119 3.245869 6.404369 0Con un nivel de significancia del 0.05, se tiene evidencia estadistica para concluir que se presentan diferencias significativas entre los cuatro genotipos.
Supuestos del modelo
##Normalidad
shapiro.test(mod1$residuals)##
## Shapiro-Wilk normality test
##
## data: mod1$residuals
## W = 0.996, p-value = 0.9837-Los residuales del modelo son normales
##Igualdad de varianzas
bartlett.test(mod1$residuals,df$Accesion)##
## Bartlett test of homogeneity of variances
##
## data: mod1$residuals and df$Accesion
## Bartlett's K-squared = 8.8102, df = 3, p-value = 0.03192-Las varianzas son diferentes
Dependencia espacial
dist_matrix <- as.matrix(dist(cbind(df$Accesion,df$DBC)))#;dist_matrix
which.max(dist_matrix) ## [1] 91max(dist_matrix) # Mayor valor ## [1] 3min(dist_matrix) # Menor valor## [1] 0dim(df)## [1] 120 4dist_matrix_inv <- 1 / dist_matrix # Element wise #inversa distancia
dist_matrix_inv[is.infinite(dist_matrix_inv)]<-0
diag(dist_matrix_inv) <- 0library(ape)## Warning: package 'ape' was built under R version 4.1.3Moran.I(df$CBD, dist_matrix_inv)## $observed
## [1] -0.08761466
##
## $expected
## [1] -0.008403361
##
## $sd
## [1] 0.008130559
##
## $p.value
## [1] 1.987686e-22library(writexl)## Warning: package 'writexl' was built under R version 4.1.3write_xlsx(df,"datosPAOLAOSPINA")