ICCplot {iarm}

Item Characteristic Curves

Description

Plots Item Characteristic Curves for dichotomous and polytomous items. The plot can display observed scores as total scores (method="score") or as average scores within adjacent class intervals (method="cut"). Class intervals can be useful when the sample size is not large enough to contain an adequate number of respondents with the same total score for each possible total score. The function includes the option to plot observed scores according to values of an exogenous variable to evaluate differential item functioning (dif="yes").

Usage

ICCplot(
  data,
  itemnumber,
  pallete = "Paired",
  xticks = 1,
  yticks = 0.5,
  thetain = -6,
  thetaend = 6,
  method = "score",
  grid = "yes",
  cinumber = 6,
  itemdescrip = "",
  axis.rumm = "yes",
  dif = "no",
  difvar = NA,
  diflabels = c("Group1", "Group 2", "Group 3", "Group 4", "Group5"),
  difstats = "yes",
  title = "Item Characteristic Curve",
  icclabel = "yes",
  xaxistitle = "Theta",
  yaxistitle = "Item Score"
)

Arguments

data

An object of class "data.frame" containing the items (include all items present in the model). The variables need to be numeric.

itemnumber

A numeric vector indicating the columns of the data (the items) which ICCs are going to be plotted. Maximum of four items per plot.

pallete

An object of class "character". Choose a pre-made color pallete from package RColorBrewer. Only available for dif="no".

xticks

A numeric scalar. Specify x-axis tick values.

yticks

A numeric scalar. Specify y-axis tick values.

thetain

A numeric scalar. Specify minimum theta values for person parameters.

thetaend

A numeric scalar. Specify maximum theta values for person parameters.

method

The method for displaying observed scores. Choose "score" to plot total scores. Choose "cut" to plot class intervals.

grid

Chooses whether the background grid should be displayed. Options are "yes" or "no".

cinumber

A numeric scalar. The number of adjacent class intervals in which participants will be divided. Notice that the number of class intervals cannot be higher than the number of total scores.

itemdescrip

A character vector indicating the description of the plotted items. Maximum of four descriptions (one description per item plotted).

axis.rumm

Configures whether the plot should display the entire trait range or solely the trait range close to the observed scores (similar to private software RUMM2030). Options are "yes" or "no".

dif

Configures whether the observed scores will be plotted according to values of an exogenous variable to evaluate differential item function. Options are "yes" or "no".

difvar

Chooses the variable which will be used to evaluate differential item functioning. Only necessary when dif="yes".

diflabels

A character vector indicating the labels to values of the variable chosen to evaluate differential item functioning. Only necessary when dif="yes".

difstats

Displays the partial gamma coefficient to indicate the magnitude of differential item functioning. Options are "yes" or "no". Only necessary when dif="yes".

title

A character vector. The title of the plot.

icclabel

Displays the labels of Expected Item Score and Observed Item Score. Options are "yes" or "no".

xaxistitle

A character vector. The x-axis title.

yaxistitle

A character vector. The y-axis title.

Author(s)

Pedro Henrique Ribeiro Santiago [e-mail], Marianne Mueller

Examples

## Not run: # Creates a plot for Item 1 using total scores
ICCplot(desc2[,5:13], itemnumber=1, method="score", itemdescrip="Item 1")

# Creates a plot for Item 1 using 8 class intervals
ICCplot(desc2[,5:13], itemnumber=1, method="cut", cinumber=8, itemdescrip="Item 1")

# Creates a plot for Item 1 using 8 class intervals without RUMM style axis
ICCplot(desc2[,5:13], itemnumber=1, method="cut", cinumber=8, itemdescrip="Item 1", axis.rumm="no")

# Creates a plot for Item 3 using 8 class intervals and evaluating DIF according to gender
ICCplot(desc2[,5:13], itemnumber=3, method="cut", cinumber=8, itemdescrip="Item 3",
dif="yes", difvar=desc2$gender, diflabels=c("Men", "Women"))

# Creates a plot with three items using 5 class intervals and evaluating DIF according to gender
ICCplot(desc2[,5:13], itemnumber=1:3, method="cut", cinumber=5,
itemdescrip=c("Item 1","Item 2","Item 3"), dif="yes"
difvar=desc2$gender, diflabels=c("Men", "Women"))

## End(Not run)