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
trt <- params$trt
trt.lab <- params$trt.lab
nct <- nchar(trt.lab)
trt.lab.s <- paste0(trt.lab, "s")
trt.lab.c <- paste0(toupper(substr(trt.lab, 1, 1)), substr(trt.lab, 2, nct))
trt.lab.sc <- paste0(toupper(substr(trt.lab, 1, 1)), substr(trt.lab, 2, nct), "s")
eu <- params$eu
mc <- params$mc

# Get means if subsamples

if (!is.null(eu)) {
  dfr2 <- dfr
  dfr <- docomp(dfr, "mean", vars, c(trt, eu))
}

# Check factors structure

out <- ck.fs(dfr, trt, NULL)
dfr <- out$dfr
nt <- out$nl[[1]]
nmis.fac <- out$nmis.fac

1. Model specification and data description

Data from r nt r trt.lab.s have been evaluated using a completely randomized design. The statistical model is $$ y_{ij} = \mu + \tau_i + \epsilon_{ij} $$ where

$y_{ij}$ is the observed response with r trt.lab $i$ and replication $j$.
$\mu$ is the mean response over all r trt.lab.s and replications.
$\tau_i$ is the effect for r trt.lab $i$.
$\epsilon_{ij}$ is the error term.

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

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)) {
  lc <- ck.crd(dfr, vars[i], trt)
  if (lc$ng.0 == 0 & lc$nrep > 1 & lc$ng > 2) {
    out <- c(out, knit_expand('child_crd.Rmd'))
  } else {
    out <- c(out, knit_expand('child_crd_fail.Rmd'))
  }
}