To add a single item, theta should be a vector of latent
scores. To add multiple items at a time, theta should be a
matrix with one item in each column. Item names can be given as
the colnames of theta.
The interpretation of theta depends on the context where the
data were generated. For example, in chess, theta represents
unobserved chess skill that is partially revealed by match
outcomes.
The graph can be regarded as undirected, but data are generated
relative to the order of vertices within each row. Vertices do not
commute. For example, a -1 for vertices ‘a’ and
‘b’ is the same as 1 for vertices ‘b’ and
‘a’.
generateItem(df, theta, th = 0.5, name, ..., scale = 1, alpha = 1)The given data.frame df with additional columns for each item.
a data frame with pairs of vertices given in columns pa1 and pa2, and item response data in other columns
a vector or matrix of absolute latent scores. See details below.
a vector of thresholds
a vector of item names
Not used. Forces remaining arguments to be specified by name.
a vector of scaling constants
a vector of item discriminations
See cmp_probs for details.
Other item generators:
generateCovItems(),
generateFactorItems(),
generateSingleFactorItems()
df <- roundRobinGraph(letters[1:5], 40)
df <- generateItem(df)
Run the code above in your browser using DataLab