Learn R Programming

catR (version 1.0)

startItems: Selection of the first items

Description

This command selects the first items of the adaptive test, either randomly or on the basis of their difficulty level.

Usage

startItems(it, fixItems=NULL, seed=NULL, nrItems=1,
 	 theta=0, bw=4, range=c(-4,4))

Arguments

it
numeric: a matrix with one row per item and four columns, with the values of the discrimination, the difficulty, the pseudo-guessing and the inattention parameters (in this order).
fixItems
either a vector of integer values or NULL (default). See Details.
seed
either a numeric value or NULL (default). See Details.
nrItems
numeric: the number of starting items to be selected (default is 1). Ignored if fixItems is not NULL.
theta
numeric: the initial ability level for selecting the first items (default is 0). Ignored if either fixItems or seed is not NULL. See Details.
bw
numeric: the length (bandwidth) of the difficulty interval for selecting the first items (default is 4). Ignored if either fixItems or seed is not NULL. See Details.
range
numeric: the range of diffiulty levels for selecting the first items (default is c(-4,4)). Ignored if either fixItems or seed is not NULL. See Details.

Value

  • A list with three arguments:
  • itemsthe selected items (identified by their number in the item bank).
  • parthe matrix of item parameters of the selected items (one row per item).
  • bOptthe values of the item difficulties chosen for selecting the first items.

Details

The first items of the adaptive test can be selected either by fixing these items or by some selection into the item bank. The first items can be fixed by specifying fixItems as a vector of integer values, each value referring to the corresponding item in the item bank. If fixItems is kep to NULL (the default choice), then nrItems will be selected, either randomly or according to their difficulty level. In the former, one has to assign a numeric value to the seed argument. In the latter, seed is kept to NULL (the default value) and the items are selected as follows. The arguments theta and bw permit to define a sequence of value, ranging from theta - bw to theta + bw and of length nrItems (if nrItems equals 1, the range reduces to theta). Then, for each value in the sequence, the function selects the item in the item bank with difficulty level as close as possible to the sequential value. By default, theta equals 0 and bw equals 4, meaning that the sequence ranges from -4 to 4 and of length nrItems. The argument range permits to constraint the range of difficulty levels, by default to the range [-4, 4].

Examples

Run this code
# Loading the 'tcals' parameters 
 data(tcals)
 tcals <- as.matrix(tcals)
 
 # Selecting 1 starting item, initial ability estimate is 0
 startItems(tcals) 

 # Selecting 3 starting items, initial ability estimate is 1
 # and bandwidth is 2
 startItems(tcals, nrItems=3, theta=1, bw=2) 

 # Selecting 5 starting items, initial ability estimate is 2
 # and bandwidth is 3
 startItems(tcals, nrItems=5, theta=2, bw=3) 

 # Random selection of 4 starting items
 startItems(tcals, seed=1, nrItems=4)

 # Selection of the first 5 starting items
 startItems(tcals, fixItems=1:5)

Run the code above in your browser using DataLab