meddiff_fit: Extract module effects from the median differences

In DavidFirth/norman: Package for Warwick Statistics module marks analysis

Extract module effects from the median differences

Description

Extract module effects from the median differences

Usage

meddiff_fit(m)

Arguments

m	A numeric matrix of median differences as computed by meddiff

Value

A lm model object

Examples

#
# Toy example from
# https://davidfirth.github.io/blog/2019/04/26/robust-measurement-from-a-2-way-table/
#
x <- structure(c(NA, NA, 10, NA, NA, 20, NA, NA, 30, 45, 55, NA, 60, 60, 50),
  .Dim = c(3L, 5L), .Dimnames = structure(list(student = c("i", "j", "k"),
  module = c("A", "B", "C", "D", "E")), .Names = c("student", "module")))
print(x)
md <- meddiff(x, threshold = 1)
the_fit <- meddiff_fit(md)$coef
names(the_fit) <- gsub("^X", "", names(the_fit))
the_fit

DavidFirth/norman documentation built on June 30, 2022, 6:05 p.m.