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
mpf <- params$mpf
spf <- params$spf
rep <- params$rep
pe <- params$pe

# Check factors structure

out <- ck.fs(dfr, c(mpf, spf), rep)
nmpf <- out$nl[[1]]
nspf <- out$nl[[2]]
nrep <- out$nrep
dfr <- out$dfr
nmis.fac <- out$nmis.fac

1. Model specification and data description

There are data for a split-plot design with r nmpf levels for the main plot factor, r nspf levels for the sub-plot factor, and r nrep replications for the main plot factor. The statistical model is $$ y_{ijk} = \mu + \alpha_i + \beta_j + \gamma_k + (\alpha\beta){ij} + (\alpha\gamma){ik} + (\beta\gamma){jk} + (\alpha\beta\gamma){ijk} $$ where

• $y_{ijk}$ is the observed response with level $i$ of the main plot factor, level $j$ of the sub-plot factor, and replication $k$.
• $\mu$ is the mean response over all levels of factors and replications.
• $\alpha_i$ is the effect for level $i$ of the main plot factor.
• $\beta_j$ is the effect for level $j$ of the sub-plot factor.
• $\gamma_k$ is the effect of replication $k$.
• $(\alpha\beta){ij}$, $(\alpha\gamma){ik}$, $(\beta\gamma){jk}$, $(\beta\gamma){jk}$, and $(\alpha\beta\gamma)_{ijk}$ the corresponding interactions.

In this model $(\alpha\gamma){ik}$ is the error term for the main plot factor, and $(\beta\gamma){jk}$ and $(\alpha\beta\gamma)_{ijk}$ are pooled to form the error term for the split-plot factor.

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

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

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