Processing CQmodel objects for plotting
The itemData and personData functions take CQmodel objects (or ConQuest output files) as inputs and return a vector or matrix. They were originally developed for use by wrightMap, but are separated out here to allow the outputs to be sent to other plotting functions.
itemData(thresholds, ...) ## Default S3 method: itemData(thresholds, item.type = "deltas",...) ## S3 method for class 'character' itemData(thresholds, p.type = NULL, equation = NULL, ...) ## S3 method for class 'CQmodel' itemData(thresholds, item.table = NULL, interactions = NULL, step.table = NULL, item.type = "default", throld = 0.5, ...) personData(thetas,...) ## Default S3 method: personData(thetas,...) ## S3 method for class 'character' personData(thetas, p.type = NULL,...) ## S3 method for class 'CQmodel' personData(thetas,...)
itemData arguments:
thresholds |
Usually, a CQmodel object or the name of a ConQuest show file. Will also accept a matrix, but this is only really for use within other functions. In general |
item.type |
Indicates whether to use |
equation |
string giving the model equation, if the Summary of Estimation table was not included in the show file. |
item.table |
Name of RMP table to use for the main effect of the item parameters. |
interactions |
Name of RMP interaction table to use in addition to |
step.table |
Name of RMP table to use in addition to |
throld |
The probability level to be used for calculating thresholds. |
... |
Additional parameters to pass to |
personData arguments:
thetas |
a CQModel object or the name of the Conquest person parameters file (EAPs, MLEs, etc.) |
p.type |
Type of person parameter estimate (EAP, MLE or WLE). |
The itemData and personData functions are usually called by wrightMap. They can also be called directly.
For the itemData function, note that the item.table, interactions, and step.table parameters must be the exact name of specific RMP tables. You cannot specify an interactions table or a step table without also specifying an item table (although JUST an item table is fine). If your model equation is more complicated, you will have to either use a GIN table or specify in the function call which tables to use for what. A model of the form item + item * step + booklet, for example, will not run unless there is a GIN table or you have defined at least the item.table.
The itemData functions return a vector of item parameters, or a matrix in which the rows are items and the columns are steps. The personData functions return a vector of person paramenters, or a matrix in which the rows are persons and the columns are dimensions.
Rebecca Freund and David Torres Irribarra
#As a call from wrightMap:
fpath <- system.file("extdata", package="WrightMap")
model1 <- CQmodel(file.path(fpath,"ex2a.eap"), file.path(fpath,"ex2a.shw"))
# Making thresholds if there are no GIN tables (partial credit model)
wrightMap(model1, type = "thresholds")
#Complex model:
model2 <- CQmodel(file.path(fpath,"ex4a.mle"), file.path(fpath,"ex4a.shw"))
wrightMap(model2, item.table = "rater")
wrightMap(model2, item.table = "rater", interactions = "rater*topic",
step.table = "topic")
# Plotting item results
fpath <- system.file("extdata", package="WrightMap")
model3 <- CQmodel(file.path(fpath,"ex2a.eap"), file.path(fpath,"ex2a.shw"))
m3.item <- itemData(model3)
dev.new(width=10, height=10)
#control of oma allows us to give more space to longer item names
itemModern(m3.item, label.items.srt= 90, oma = c(2,0,0,2))
itemClassic(m3.item)
itemHist(m3.item)
m3.person <- personData(model3)
personHist(m3.person)
personDens(m3.person)Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.