In damian-t-p/halfsibdesign: What the Package Does (One Line, Title Case)

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

halfsibdesign

A package containing several algorithms for finding REML estimates for covariances in the balanced $q$-dimensional half-sib design y_ijk = $\mu$ + $\alpha$_i + $\beta$_ij + $\epsilon$_ijk, $1\leq i \leq I, 1\leq j \leq J, 1\leq k \leq K$, where $\alpha$_i $\sim \mathcal{N}(0, A)$, $\beta$_ij $\sim \mathcal{N}(0, B)$, $\epsilon$_ijk $\sim \mathcal{N}(0, E)$.

Installation

You can install the development version of halfsibdesign from GitHub with:

# install.packages("devtools")
devtools::install_github("damian-t-p/halfsibdesign")

Example

Simulate a half-sib experiment with specified parameters:

set.seed(1)

library(halfsibdesign)

q <- 4 # number of traits

I <- 100 # number of sires
J <- 3 # number of dams
K <- 5 # number of individuals per line

mu <- 1:q

sigma_a <- 5
sigma_b <- 3
sigma_e <- 1

A <- sigma_a^2 * diag(c(0, 0, 1, 1))
B <- sigma_b^2 * diag(q)
E <- sigma_e^2 * diag(q)

df <- rhalfsib(mu, A, I, B, J, E, K)

First, perform a MANOVA fit

manova_2way(df)

Notice that S3, the within-sires estimate is not non-negative definite, se we compute the correponding REML estimate.

stepreml_2way(df)

damian-t-p/halfsibdesign documentation built on March 14, 2023, 4:55 a.m.