setwd("/Volumes/GoogleDrive/Mi unidad/Agrosavia/Colaboraciones/Laura")
datos6<-read.table("mirafloresflo.csv", header=T, sep=',')
datos6$gen<-as.factor(datos6$gen)
datos6$bloque<-as.factor(datos6$bloque)
attach(datos6)
library(ggplot2)
library(Rmisc)
## Loading required package: lattice
## Loading required package: plyr
library(emmeans)
#Gráfica cojines por planta
ggplot(datos6, aes(y=cojplanta, x=gen, fill= gen, colour=gen)) +
geom_bar(position="dodge", stat="identity") +
labs(x="Genotipo", y="Cojines por planta")
# Gráfica frutos por planta
ggplot(datos6, aes(fill=gen, y=frutos, x=gen, colour=gen)) +
geom_bar(position="dodge", stat="identity") +
labs(x="Genotipo", y="Frutos por planta")
#modelos
gfit1<-glm(cojplanta~gen, data=datos6, family = poisson (link=log))
gfit2<-glm(frutos~gen, data=datos6, family = poisson (link=log))
# resultado cojines por planta
summary(gfit1)
##
## Call:
## glm(formula = cojplanta ~ gen, family = poisson(link = log),
## data = datos6)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -10.303 -4.407 -1.711 1.796 34.751
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.459905 0.056254 43.728 < 2e-16 ***
## genTCS 02 1.165916 0.064426 18.097 < 2e-16 ***
## genTCS 03 0.541367 0.070754 7.651 1.99e-14 ***
## genTCS 04 -0.038715 0.080337 -0.482 0.630
## genTCS 05 -1.465283 0.129858 -11.284 < 2e-16 ***
## genTCS 08 -1.730390 0.144918 -11.940 < 2e-16 ***
## genTCS 10 -0.048632 0.080541 -0.604 0.546
## genTCS 11 -0.009539 0.079746 -0.120 0.905
## genTCS 12 1.369541 0.063000 21.739 < 2e-16 ***
## genTCS 20 0.432522 0.072235 5.988 2.13e-09 ***
## genTCS 40 0.545044 0.070707 7.709 1.27e-14 ***
## genTCS 41 -0.035430 0.080270 -0.441 0.659
## genTCS 42 0.689978 0.068934 10.009 < 2e-16 ***
## genTCS 43 -1.010810 0.108893 -9.283 < 2e-16 ***
## genTCS 44 -0.389766 0.088529 -4.403 1.07e-05 ***
## genTCS 45 1.511783 0.062148 24.325 < 2e-16 ***
## genTCS 46 1.396527 0.062830 22.227 < 2e-16 ***
## genTCS 47 0.351281 0.073428 4.784 1.72e-06 ***
## genTCS 48 -0.092782 0.081466 -1.139 0.255
## genTCS 49 0.337828 0.073634 4.588 4.48e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 16336 on 539 degrees of freedom
## Residual deviance: 10728 on 520 degrees of freedom
## AIC: 12526
##
## Number of Fisher Scoring iterations: 6
anova(gfit1, test = "Chisq")
## Analysis of Deviance Table
##
## Model: poisson, link: log
##
## Response: cojplanta
##
## Terms added sequentially (first to last)
##
##
## Df Deviance Resid. Df Resid. Dev Pr(>Chi)
## NULL 539 16336
## gen 19 5607.6 520 10728 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
# resultado frutos por planta
summary(gfit2)
##
## Call:
## glm(formula = frutos ~ gen, family = poisson(link = log), data = datos6)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.3817 -1.8053 -1.0541 0.1155 10.0882
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.32914 0.09901 13.424 < 2e-16 ***
## genTCS 02 -1.36688 0.21969 -6.222 4.92e-10 ***
## genTCS 03 -0.98739 0.19005 -5.195 2.04e-07 ***
## genTCS 04 -1.44692 0.22687 -6.378 1.80e-10 ***
## genTCS 05 -1.98592 0.28501 -6.968 3.21e-12 ***
## genTCS 08 -2.83321 0.42007 -6.745 1.53e-11 ***
## genTCS 10 -0.98739 0.19005 -5.195 2.04e-07 ***
## genTCS 11 -3.23868 0.50971 -6.354 2.10e-10 ***
## genTCS 12 0.20334 0.13343 1.524 0.127524
## genTCS 20 -0.10318 0.14378 -0.718 0.472979
## genTCS 40 -0.32091 0.15270 -2.102 0.035592 *
## genTCS 41 -0.15906 0.14594 -1.090 0.275740
## genTCS 42 -0.59962 0.16632 -3.605 0.000312 ***
## genTCS 43 -1.91692 0.27649 -6.933 4.12e-12 ***
## genTCS 44 -0.67373 0.17039 -3.954 7.69e-05 ***
## genTCS 45 -0.84078 0.18036 -4.662 3.14e-06 ***
## genTCS 46 1.34373 0.11118 12.086 < 2e-16 ***
## genTCS 47 -0.53063 0.16269 -3.262 0.001108 **
## genTCS 48 -1.06962 0.19590 -5.460 4.76e-08 ***
## genTCS 49 -0.88730 0.18334 -4.840 1.30e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 3776.7 on 539 degrees of freedom
## Residual deviance: 2513.6 on 520 degrees of freedom
## AIC: 3241.6
##
## Number of Fisher Scoring iterations: 6
anova(gfit2, test = "Chisq")
## Analysis of Deviance Table
##
## Model: poisson, link: log
##
## Response: frutos
##
## Terms added sequentially (first to last)
##
##
## Df Deviance Resid. Df Resid. Dev Pr(>Chi)
## NULL 539 3776.7
## gen 19 1263.1 520 2513.6 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Contrastes para Cojines
#Gen
contrast <- emmeans(gfit1, ~ gen)
plot(contrast, comparisons = TRUE, xlab ="LN(Cojines por planta)")
cld_gen <-multcomp::cld(contrast, alpha = 0.05, Letters = LETTERS, reversed=T)
cld_gen
## gen emmean SE df asymp.LCL asymp.UCL .group
## TCS 45 3.972 0.0264 Inf 3.920 4.023 A
## TCS 46 3.856 0.0280 Inf 3.802 3.911 AB
## TCS 12 3.829 0.0284 Inf 3.774 3.885 B
## TCS 02 3.626 0.0314 Inf 3.564 3.687 C
## TCS 42 3.150 0.0398 Inf 3.072 3.228 D
## TCS 40 3.005 0.0428 Inf 2.921 3.089 DE
## TCS 03 3.001 0.0429 Inf 2.917 3.085 DE
## TCS 20 2.892 0.0453 Inf 2.804 2.981 E
## TCS 47 2.811 0.0472 Inf 2.719 2.904 E
## TCS 49 2.798 0.0475 Inf 2.705 2.891 E
## TCS 01 2.460 0.0563 Inf 2.350 2.570 F
## TCS 11 2.450 0.0565 Inf 2.340 2.561 F
## TCS 41 2.424 0.0573 Inf 2.312 2.537 F
## TCS 04 2.421 0.0574 Inf 2.309 2.534 F
## TCS 10 2.411 0.0576 Inf 2.298 2.524 F
## TCS 48 2.367 0.0589 Inf 2.252 2.483 FG
## TCS 44 2.070 0.0684 Inf 1.936 2.204 G
## TCS 43 1.449 0.0932 Inf 1.266 1.632 H
## TCS 05 0.995 0.1170 Inf 0.765 1.224 HI
## TCS 08 0.730 0.1336 Inf 0.468 0.991 I
##
## Results are given on the log (not the response) scale.
## Confidence level used: 0.95
## P value adjustment: tukey method for comparing a family of 20 estimates
## significance level used: alpha = 0.05
## NOTE: Compact letter displays can be misleading
## because they show NON-findings rather than findings.
## Consider using 'pairs()', 'pwpp()', or 'pwpm()' instead.
#Contrastes para frutos
#Gen
contrast2 <- emmeans(gfit2, ~ gen)
plot(contrast2, comparisons = TRUE, xlab = "LN(Frutos por planta)")
cld_gen <-multcomp::cld(contrast2, alpha = 0.05, Letters = LETTERS, reversed=T)
cld_gen
## gen emmean SE df asymp.LCL asymp.UCL .group
## TCS 46 2.6729 0.0506 Inf 2.5738 2.7720 A
## TCS 12 1.5325 0.0894 Inf 1.3572 1.7078 B
## TCS 01 1.3291 0.0990 Inf 1.1351 1.5232 BC
## TCS 20 1.2260 0.1043 Inf 1.0216 1.4303 BCD
## TCS 41 1.1701 0.1072 Inf 0.9599 1.3802 BCD
## TCS 40 1.0082 0.1162 Inf 0.7804 1.2361 CDE
## TCS 47 0.7985 0.1291 Inf 0.5455 1.0515 CDEF
## TCS 42 0.7295 0.1336 Inf 0.4676 0.9914 DEFG
## TCS 44 0.6554 0.1387 Inf 0.3836 0.9272 DEFG
## TCS 45 0.4884 0.1508 Inf 0.1929 0.7838 EFG
## TCS 49 0.4418 0.1543 Inf 0.1394 0.7443 EFGH
## TCS 10 0.3417 0.1622 Inf 0.0238 0.6597 EFGHI
## TCS 03 0.3417 0.1622 Inf 0.0238 0.6597 EFGHI
## TCS 48 0.2595 0.1690 Inf -0.0718 0.5908 FGHI
## TCS 02 -0.0377 0.1961 Inf -0.4221 0.3466 GHIJ
## TCS 04 -0.1178 0.2041 Inf -0.5179 0.2823 GHIJ
## TCS 43 -0.5878 0.2582 Inf -1.0938 -0.0818 HIJ
## TCS 05 -0.6568 0.2673 Inf -1.1806 -0.1330 IJ
## TCS 08 -1.5041 0.4082 Inf -2.3042 -0.7039 J
## TCS 11 -1.9095 0.5000 Inf -2.8895 -0.9296 J
##
## Results are given on the log (not the response) scale.
## Confidence level used: 0.95
## P value adjustment: tukey method for comparing a family of 20 estimates
## significance level used: alpha = 0.05
## NOTE: Compact letter displays can be misleading
## because they show NON-findings rather than findings.
## Consider using 'pairs()', 'pwpp()', or 'pwpm()' instead.
detach(datos6)