TestGardener (version 3.3.6)

scoreDensity: Compute and plot a score density histogram and and curve.

Description

The tasks of function index.density() and plotting the density are combined. The score density is plotted both as a histogram and as a smooth curve. All the score types may be plotted: sum scores, expected test scores, percentile score index values, and locations on the test information or scale curve. The plot is output as a ggplot2 plot object, which is actually plotted using the print command.

Usage

scoreDensity(scrvec, scrrng=c(0,100), ndensbasis=15, ttlstr=NULL, pltmax=0)

Value

A ggplot2 plot object dens.plot that can be displayed using command

print(dens.plot).

Arguments

scrvec

A vector of strictly increasing bin boundary values, with the first at the lowest plotting value and the last at the upper boundary. The number of bins in the histogram is one less than the number of bndry values.

scrrng

A vector of length 2 containing lower and upper boundaries on scores, which defaults to c(0,100).

ndensbasis

The number of spline basis functions to be used to represent the smooth density curve.

ttlstr

A string object used as a title for the plot. Defaults to none.

pltmax

An upper limit on the vertical axis for plotting. Defaults to the maximum curve value.

Author

Juan Li and James Ramsay

References

Ramsay, J. O., Li J. and Wiberg, M. (2020) Full information optimal scoring. Journal of Educational and Behavioral Statistics, 45, 297-315.

Ramsay, J. O., Li J. and Wiberg, M. (2020) Better rating scale scores with information-based psychometrics. Psych, 2, 347-360.

See Also

index_fun, index2info, mu, index_distn

Examples

#  Example 1.  Display probability density curves for the 
#  short SweSAT multiple choice test with 24 items and 1000 examinees
SfdList <- Quant_13B_problem_parmList$SfdList
index   <- Quant_13B_problem_parmList$index
Qvec    <- Quant_13B_problem_parmList$Qvec
#  plot the density for the score indices within interval c(0,100)
index_int <- index[0 < index & index < 100]
oldpar <- par(no.readonly=TRUE)
scoreDensity(index_int)
par(oldpar)