In reyzaguirre/pepa: Package for the Execution of Pre Cooked Analysis

library(knitr)
opts_chunk$set(echo = FALSE, comment = NA)

# Pass arguments

dfr <- params$dfr
vars <- params$vars
geno <- params$geno
rep <- params$rep
block <- params$block
k <- params$k
method <- params$method

# Check factors structure

out <- ck.fs(dfr, c(geno, block), rep)
dfr <- out$dfr
ng <- out$nl[[1]]
nrep <- out$nrep
nib <- out$nl[[2]]
nmis.fac <- out$nmis.fac

# Define internal variables

block <- dfr[, block]
geno <- dfr[, geno]
rep <- dfr[, rep]

if (method == "VC")
  geno <- as.factor(geno)

1. Model specification and data description

There are data for r ng genotypes tested using an alpha (0,1) design with r nrep replications and r nib incomplete blocks. In this design each replication is a complete block for the genotypes that is splitted in several incomplete blocks. The statistical model is $$ y_{ijk} = \mu + \tau_i + \gamma_j + \rho_{k(j)} + \epsilon_{ijk} $$ where

• $y_{ijk}$ is the observed response with genotype $i$, replication $j$, incomplete block $k$.
• $\mu$ is the mean response over all genotypes and replications.
• $\tau_i$ is the effect for genotype $i$.
• $\gamma_j$ is the effect for replication $j$.
• $\rho_{k(j)}$ is the effect of the incomplete block $k$ which is nested into replication $j$.
• $\epsilon_{ijk}$ is the error term.

In this model we assume that the errors are independent and have a normal distribution with common variance, that is, $\epsilon_{ijk} \sim N(0,\sigma_{\epsilon}^2)$.

r if (nmis.fac == 1) paste("Note: There is", nmis.fac, "row with missing values for classifications factors. This row has been deleted.") r if (nmis.fac > 1) paste("Note: There are", nmis.fac, "rows with missing values for classifications factors. These rows have been deleted.")

out <- NULL
for (i in 1:length(vars))
  out <- c(out, knit_expand('child_a01d.Rmd'))

r paste(knit(text = out), collapse = '\n')

reyzaguirre/pepa documentation built on March 29, 2025, 9:56 p.m.