library(car)
## Warning: package 'car' was built under R version 4.2.3
## Loading required package: carData
library(faux)
##
## ************
## Welcome to faux. For support and examples visit:
## https://debruine.github.io/faux/
## - Get and set global package options with: faux_options()
## ************
options(digits=4)
DFL1=rnorm_multi(n=24,vars = 3,mu = c(15,15.2,15.4),sd = c(1.2,1.2,1.25),r = c(0.7,0.8,0.81),
varnames=c("Lpre1","Lpre2","Lpre3"))
DFL2=rnorm_multi(n=24,vars = 3,mu = c(16,16.2,16.5),sd = c(1.1,1.05,1.15),r = c(0.72,0.82,0.84),
varnames=c("Lpost1","Lpost2","Lpost3"))
DFL3=rnorm_multi(n=24,vars = 3,mu = c(16.8,17.2,17.5),sd = c(1.12,1.15,1.08),r = c(0.74,0.83,0.86),
varnames=c("Lpost2_1","Lpost2_2","Lpost2_3"))
dfd1=data.frame(DFL1,DFL2,DFL3,trt=gl(3,8,48,labels=c("trt0","trt1","trt2")),pos=gl(2,12,48,labels=c("interno","externo")))
View(dfd1)
names(dfd1)
## [1] "Lpre1" "Lpre2" "Lpre3" "Lpost1" "Lpost2" "Lpost3"
## [7] "Lpost2_1" "Lpost2_2" "Lpost2_3" "trt" "pos"
contrasts(dfd1$trt)
## trt1 trt2
## trt0 0 0
## trt1 1 0
## trt2 0 1
xtabs(~ trt, data=dfd1)
## trt
## trt0 trt1 trt2
## 16 16 16
xtabs(~ pos, data=dfd1)
## pos
## interno externo
## 24 24
########################## formato largo
library(readxl)
dfl <- read_excel("G:/Mi unidad/MAESTRÍA CIENCIA Y TECNOLOGÍA ALIMENTOS/Métodos Multivariados/Entregables/1.3/L_033023.xlsx",
sheet = "h2F2")
some(dfl)
## # A tibble: 10 × 6
## L trt fase hora id pos
## <dbl> <chr> <chr> <dbl> <dbl> <chr>
## 1 14.3 trt0 pre 1 7 interno
## 2 16.1 trt0 pre 2 6 externo
## 3 16.3 trt0 pre 2 8 interno
## 4 14.5 trt1 pre 2 16 externo
## 5 17.1 trt1 pre 3 15 interno
## 6 16.7 trt2 post1 1 22 interno
## 7 16.3 trt0 post1 2 6 externo
## 8 17.1 trt2 post1 3 23 interno
## 9 17.2 trt0 post2 2 8 externo
## 10 17.5 trt0 post2 3 5 externo
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.2.3
##
## Attaching package: 'dplyr'
## The following object is masked from 'package:car':
##
## recode
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
dfmedias=dfl %>%
group_by(trt,fase,hora,pos) %>%
summarise(n = n(),Lmedia = mean(L, na.rm = TRUE))
## `summarise()` has grouped output by 'trt', 'fase', 'hora'. You can override
## using the `.groups` argument.
dfmedias
## # A tibble: 54 × 6
## # Groups: trt, fase, hora [27]
## trt fase hora pos n Lmedia
## <chr> <chr> <dbl> <chr> <int> <dbl>
## 1 trt0 post1 1 externo 8 16.3
## 2 trt0 post1 1 interno 8 16.1
## 3 trt0 post1 2 externo 8 16.5
## 4 trt0 post1 2 interno 8 16.0
## 5 trt0 post1 3 externo 8 16.6
## 6 trt0 post1 3 interno 8 16.5
## 7 trt0 post2 1 externo 8 16.6
## 8 trt0 post2 1 interno 8 16.7
## 9 trt0 post2 2 externo 8 17.1
## 10 trt0 post2 2 interno 8 17.2
## # ℹ 44 more rows
library(lattice)
xyplot(Lmedia ~ hora | fase*trt, groups=pos, type="b",data=dfmedias,auto.key = list(2, cex = 0.8, title = "Posición", text = c("Interno", "Externo"), points = TRUE))
#xyplot(Lmedia ~ hora | fase+trt, groups=trt, type="b",data=dfmedias)
mod.ok <- lm(cbind(Lpre1,Lpre2,Lpre3,Lpost1,Lpost2,Lpost3,Lpost2_1,Lpost2_2,Lpost2_3)~factor(pos)+factor(trt),data=dfd1)
mod.ok
##
## Call:
## lm(formula = cbind(Lpre1, Lpre2, Lpre3, Lpost1, Lpost2, Lpost3,
## Lpost2_1, Lpost2_2, Lpost2_3) ~ factor(pos) + factor(trt),
## data = dfd1)
##
## Coefficients:
## Lpre1 Lpre2 Lpre3 Lpost1 Lpost2 Lpost3
## (Intercept) 14.4045 14.9209 14.8845 16.2165 16.1737 16.6193
## factor(pos)externo 0.9795 1.1547 1.2874 0.4670 0.9706 0.4432
## factor(trt)trt1 -0.1075 -0.5411 -0.2089 -0.7535 -0.3037 -0.6880
## factor(trt)trt2 0.0107 -0.2712 -0.2648 -0.9497 -1.1120 -0.6374
## Lpost2_1 Lpost2_2 Lpost2_3
## (Intercept) 16.3259 16.9886 17.2903
## factor(pos)externo 0.2716 -0.6362 -0.1828
## factor(trt)trt1 0.2154 0.3011 0.3023
## factor(trt)trt2 -0.1810 0.3458 0.1124
summary(mod.ok)
## Response Lpre1 :
##
## Call:
## lm(formula = Lpre1 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5943 -0.6619 0.0534 0.3898 2.0023
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 14.4045 0.2343 61.48 <2e-16 ***
## factor(pos)externo 0.9795 0.4686 2.09 0.042 *
## factor(trt)trt1 -0.1075 0.4058 -0.26 0.792
## factor(trt)trt2 0.0107 0.5739 0.02 0.985
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.937 on 44 degrees of freedom
## Multiple R-squared: 0.234, Adjusted R-squared: 0.182
## F-statistic: 4.48 on 3 and 44 DF, p-value: 0.00785
##
##
## Response Lpre2 :
##
## Call:
## lm(formula = Lpre2 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.673 -0.417 0.173 0.554 1.553
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 14.921 0.198 75.46 <2e-16 ***
## factor(pos)externo 1.155 0.395 2.92 0.0055 **
## factor(trt)trt1 -0.541 0.342 -1.58 0.1213
## factor(trt)trt2 -0.271 0.484 -0.56 0.5783
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.791 on 44 degrees of freedom
## Multiple R-squared: 0.326, Adjusted R-squared: 0.28
## F-statistic: 7.1 on 3 and 44 DF, p-value: 0.00054
##
##
## Response Lpre3 :
##
## Call:
## lm(formula = Lpre3 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.938 -0.601 -0.139 0.799 1.935
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 14.885 0.242 61.46 <2e-16 ***
## factor(pos)externo 1.287 0.484 2.66 0.011 *
## factor(trt)trt1 -0.209 0.419 -0.50 0.621
## factor(trt)trt2 -0.265 0.593 -0.45 0.657
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.969 on 44 degrees of freedom
## Multiple R-squared: 0.267, Adjusted R-squared: 0.217
## F-statistic: 5.35 on 3 and 44 DF, p-value: 0.00315
##
##
## Response Lpost1 :
##
## Call:
## lm(formula = Lpost1 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.398 -0.525 -0.173 0.464 1.567
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 16.216 0.201 80.67 <2e-16 ***
## factor(pos)externo 0.467 0.402 1.16 0.252
## factor(trt)trt1 -0.754 0.348 -2.16 0.036 *
## factor(trt)trt2 -0.950 0.492 -1.93 0.060 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.804 on 44 degrees of freedom
## Multiple R-squared: 0.111, Adjusted R-squared: 0.0508
## F-statistic: 1.84 on 3 and 44 DF, p-value: 0.154
##
##
## Response Lpost2 :
##
## Call:
## lm(formula = Lpost2 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.132 -0.758 0.227 0.704 1.829
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 16.174 0.260 62.28 <2e-16 ***
## factor(pos)externo 0.971 0.519 1.87 0.068 .
## factor(trt)trt1 -0.304 0.450 -0.68 0.503
## factor(trt)trt2 -1.112 0.636 -1.75 0.087 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.04 on 44 degrees of freedom
## Multiple R-squared: 0.0885, Adjusted R-squared: 0.0263
## F-statistic: 1.42 on 3 and 44 DF, p-value: 0.249
##
##
## Response Lpost3 :
##
## Call:
## lm(formula = Lpost3 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.992 -0.590 0.144 0.687 1.690
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 16.619 0.262 63.35 <2e-16 ***
## factor(pos)externo 0.443 0.525 0.84 0.40
## factor(trt)trt1 -0.688 0.454 -1.51 0.14
## factor(trt)trt2 -0.637 0.643 -0.99 0.33
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.05 on 44 degrees of freedom
## Multiple R-squared: 0.0499, Adjusted R-squared: -0.0149
## F-statistic: 0.77 on 3 and 44 DF, p-value: 0.517
##
##
## Response Lpost2_1 :
##
## Call:
## lm(formula = Lpost2_1 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.9767 -0.4236 0.0626 0.5140 1.4865
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 16.326 0.232 70.30 <2e-16 ***
## factor(pos)externo 0.272 0.464 0.58 0.56
## factor(trt)trt1 0.215 0.402 0.54 0.60
## factor(trt)trt2 -0.181 0.569 -0.32 0.75
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.929 on 44 degrees of freedom
## Multiple R-squared: 0.0345, Adjusted R-squared: -0.0313
## F-statistic: 0.525 on 3 and 44 DF, p-value: 0.668
##
##
## Response Lpost2_2 :
##
## Call:
## lm(formula = Lpost2_2 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6141 -0.5539 0.0297 0.4593 1.1422
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 16.989 0.166 102.43 <2e-16 ***
## factor(pos)externo -0.636 0.332 -1.92 0.062 .
## factor(trt)trt1 0.301 0.287 1.05 0.300
## factor(trt)trt2 0.346 0.406 0.85 0.399
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.663 on 44 degrees of freedom
## Multiple R-squared: 0.113, Adjusted R-squared: 0.0526
## F-statistic: 1.87 on 3 and 44 DF, p-value: 0.149
##
##
## Response Lpost2_3 :
##
## Call:
## lm(formula = Lpost2_3 ~ factor(pos) + factor(trt), data = dfd1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3417 -0.4983 -0.0184 0.5818 1.7904
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 17.290 0.210 82.53 <2e-16 ***
## factor(pos)externo -0.183 0.419 -0.44 0.66
## factor(trt)trt1 0.302 0.363 0.83 0.41
## factor(trt)trt2 0.112 0.513 0.22 0.83
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.838 on 44 degrees of freedom
## Multiple R-squared: 0.0258, Adjusted R-squared: -0.0406
## F-statistic: 0.389 on 3 and 44 DF, p-value: 0.762
#(av.ok <- Anova(mod.ok, idata=idata, idesign=~fase*hora, type=3))
av.ok <- Anova(mod.ok, idesign=~fase*hora, type=3)
summary(av.ok)
##
## Type III MANOVA Tests:
##
## Sum of squares and products for error:
## Lpre1 Lpre2 Lpre3 Lpost1 Lpost2 Lpost3 Lpost2_1 Lpost2_2
## Lpre1 38.647 19.914 28.968 -1.925 -15.6761 -17.585 -4.517 -5.5771
## Lpre2 19.914 27.526 19.527 5.521 1.5091 4.839 1.126 -4.6449
## Lpre3 28.968 19.527 41.293 3.379 -6.7827 -6.727 11.480 2.7910
## Lpost1 -1.925 5.521 3.379 28.450 26.4608 28.503 8.063 4.4875
## Lpost2 -15.676 1.509 -6.783 26.461 47.4814 40.365 2.630 0.2527
## Lpost3 -17.585 4.839 -6.727 28.503 40.3645 48.452 13.713 4.0693
## Lpost2_1 -4.517 1.126 11.480 8.063 2.6297 13.713 37.969 19.0526
## Lpost2_2 -5.577 -4.645 2.791 4.487 0.2527 4.069 19.053 19.3647
## Lpost2_3 -4.348 -4.725 2.918 7.239 -4.2206 6.189 25.877 21.7270
## Lpost2_3
## Lpre1 -4.348
## Lpre2 -4.725
## Lpre3 2.918
## Lpost1 7.239
## Lpost2 -4.221
## Lpost3 6.189
## Lpost2_1 25.877
## Lpost2_2 21.727
## Lpost2_3 30.901
##
## ------------------------------------------
##
## Term: (Intercept)
##
## Sum of squares and products for the hypothesis:
## Lpre1 Lpre2 Lpre3 Lpost1 Lpost2 Lpost3 Lpost2_1 Lpost2_2 Lpost2_3
## Lpre1 3320 3439 3430 3737 3728 3830 3763 3915 3985
## Lpre2 3439 3562 3553 3871 3861 3968 3898 4056 4128
## Lpre3 3430 3553 3545 3862 3852 3958 3888 4046 4118
## Lpost1 3737 3871 3862 4208 4196 4312 4236 4408 4486
## Lpost2 3728 3861 3852 4196 4185 4301 4225 4396 4474
## Lpost3 3830 3968 3958 4312 4301 4419 4341 4517 4598
## Lpost2_1 3763 3898 3888 4236 4225 4341 4265 4438 4516
## Lpost2_2 3915 4056 4046 4408 4396 4517 4438 4618 4700
## Lpost2_3 3985 4128 4118 4486 4474 4598 4516 4700 4783
##
## Multivariate Tests: (Intercept)
## Df test stat approx F num Df den Df Pr(>F)
## Pillai 1 1.0 2909 9 36 <2e-16 ***
## Wilks 1 0.0 2909 9 36 <2e-16 ***
## Hotelling-Lawley 1 727.2 2909 9 36 <2e-16 ***
## Roy 1 727.2 2909 9 36 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## ------------------------------------------
##
## Term: factor(pos)
##
## Sum of squares and products for the hypothesis:
## Lpre1 Lpre2 Lpre3 Lpost1 Lpost2 Lpost3 Lpost2_1 Lpost2_2
## Lpre1 3.8378 4.5243 5.0441 1.8297 3.8030 1.7366 1.0642 -2.4925
## Lpre2 4.5243 5.3336 5.9464 2.1570 4.4833 2.0473 1.2546 -2.9384
## Lpre3 5.0441 5.9464 6.6296 2.4048 4.9984 2.2825 1.3987 -3.2760
## Lpost1 1.8297 2.1570 2.4048 0.8723 1.8131 0.8279 0.5074 -1.1883
## Lpost2 3.8030 4.4833 4.9984 1.8131 3.7685 1.7209 1.0546 -2.4699
## Lpost3 1.7366 2.0473 2.2825 0.8279 1.7209 0.7858 0.4816 -1.1279
## Lpost2_1 1.0642 1.2546 1.3987 0.5074 1.0546 0.4816 0.2951 -0.6912
## Lpost2_2 -2.4925 -2.9384 -3.2760 -1.1883 -2.4699 -1.1279 -0.6912 1.6188
## Lpost2_3 -0.7162 -0.8444 -0.9414 -0.3415 -0.7097 -0.3241 -0.1986 0.4652
## Lpost2_3
## Lpre1 -0.7162
## Lpre2 -0.8444
## Lpre3 -0.9414
## Lpost1 -0.3415
## Lpost2 -0.7097
## Lpost3 -0.3241
## Lpost2_1 -0.1986
## Lpost2_2 0.4652
## Lpost2_3 0.1337
##
## Multivariate Tests: factor(pos)
## Df test stat approx F num Df den Df Pr(>F)
## Pillai 1 0.5652 5.2 9 36 0.000155 ***
## Wilks 1 0.4348 5.2 9 36 0.000155 ***
## Hotelling-Lawley 1 1.3000 5.2 9 36 0.000155 ***
## Roy 1 1.3000 5.2 9 36 0.000155 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## ------------------------------------------
##
## Term: factor(trt)
##
## Sum of squares and products for the hypothesis:
## Lpre1 Lpre2 Lpre3 Lpost1 Lpost2 Lpost3 Lpost2_1 Lpost2_2
## Lpre1 0.13599 0.4801 0.08445 0.3082 -0.3351 0.4262 -0.3731 -0.1444
## Lpre2 0.48012 1.9501 0.52225 1.8922 -0.2870 2.0583 -1.1919 -0.8045
## Lpre3 0.08445 0.5223 0.24939 0.8980 0.5796 0.7513 -0.1216 -0.3487
## Lpost1 0.30823 1.8922 0.89799 3.2336 2.0665 2.7119 -0.4507 -1.2567
## Lpost2 -0.33513 -0.2870 0.57959 2.0665 3.9766 0.8963 1.3597 -0.6805
## Lpost3 0.42616 2.0583 0.75133 2.7119 0.8963 2.5381 -0.8971 -1.0926
## Lpost2_1 -0.37307 -1.1919 -0.12161 -0.4507 1.3597 -0.8971 1.0850 0.2512
## Lpost2_2 -0.14437 -0.8045 -0.34874 -1.2567 -0.6805 -1.0926 0.2512 0.4941
## Lpost2_3 -0.29284 -1.1456 -0.28003 -1.0160 0.3290 -1.1603 0.7485 0.4400
## Lpost2_3
## Lpre1 -0.2928
## Lpre2 -1.1456
## Lpre3 -0.2800
## Lpost1 -1.0160
## Lpost2 0.3290
## Lpost3 -1.1603
## Lpost2_1 0.7485
## Lpost2_2 0.4400
## Lpost2_3 0.6795
##
## Multivariate Tests: factor(trt)
## Df test stat approx F num Df den Df Pr(>F)
## Pillai 2 0.7159 2.292 18 74 0.006791 **
## Wilks 2 0.3798 2.491 18 72 0.003336 **
## Hotelling-Lawley 2 1.3811 2.686 18 70 0.001684 **
## Roy 2 1.1648 4.789 9 37 0.000291 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Se observa en los datos que el factor de tratamiento tiene mayor influencia que la posición de la medición de color en los frutos de durazno.
#Se coloca # en la función Anova ya que aparece un error en el argumento idata que no pudimos resolver.