In CIP-RIU/hidap: High Interactive Data Analysis Platform for Plant breeding

i = {{k}}

Analysis of r trts[i]

  at <- suppressWarnings(st4gi::rcbd(trts[i], treat, rep, tbl, maxp))  

  model <- aov(tbl[, trts[i]] ~ tbl[, treat] + tbl[, rep])

r if(lc$c1 == 1 & lc$c2 == 1 ) {"You have fitted a linear model for a RCBD. The ANOVA table for your model is:"}

pander::pandoc.table(at, justify = "lrrrrr", digits = 6)

r if(lc$c3 == 0) paste("You have some missing values (", format(lc$pmis * 100, digits = 3), "%) and they have been estimated before running ANOVA.")

if (at[1, 5] < 0.05 ) {
 txt = paste("The p-value for treatments is",
             format(at[1, 5], digits = 6, scientific = FALSE),
             "which is significant at the 5% level.")  
} else {
  txt = ""
}

r txt

The means of your treatments are:

x <- tapply(tbl[, trts[i]], tbl[, treat], mean)
x <- as.data.frame(x)
x <- cbind(row.names(x), x)
names(x) <- c(treat, trts[i])
row.names(x) = 1:nrow(x)
x[, 2] <- format(x[, 2], digits = 3)
x[, 2] <- as.numeric(x[, 2])
pander::pandoc.table(x, digits = 3, justify = "lr")

  #z=x[order(x[traits[i]]), ]
  z=x[order(x[2]), ]
  dotchart(z[,2], labels = z[,1])

r if(lc$nt < 10 ) {"It is always good to have some visualization of the data. Because the number of treatments in your experiment is not so big, we can plot the data for each treatment:"}

if (lc$nt < 10 ) msdplot(trts[i], treat, tbl, conf = 1)

Do not forget the assumptions of the model. It is supposed that the error has a normal distribution with the same variance for all the treatments. The following plots must help you evaluate this:

  par(mfrow = c(1, 2))
  plot(model, which = 1)
  plot(model, which = 2)

Funnel shapes for the first plot may suggest heterogeneity of variances while departures from the theoretical normal line are symptoms of lack of normality.

CIP-RIU/hidap documentation built on April 30, 2021, 9:21 p.m.