Sensitivity_plot {TestGardener}

Plots all the sensitivity curves for selected items or questions.

Description

A sensitivity curve for an option is the first derivative of the corresponding surprisal curve. Its values can be positive or negative, and the size of the departure from zero at any point on the curve is the amount information contributed by that curve to locating the value of an examinee or respondent on the score index continuum.

Usage

Sensitivity_plot(scrfine, SfdList, Qvec, dataList, plotindex=1:n, 
                 plotrange=c(min(scrfine),max(scrfine)),   
                 key=NULL, titlestr=NULL, saveplot=FALSE, width=c(-0.2,0.2), 
                 ttlsz=NULL, axisttl=NULL, axistxt=NULL, lgdlab=NULL)

Arguments

scrfine

A vector of length nfine (usually 101) containing equally spaced points spanning the plotrange. Used for plotting.

SfdList

A numbered list object produced by a TestGardener analysis of a test. Its length is equal to the number of items in the test or questions in the scale. Each member of SfdList is a named list containing information computed during the analysis.

Qvec

The values of the five marker percentiles.

dataList

A list that contains the objects needed to analyse the test or rating scale.

plotindex

A set of integers specifying the numbers of the items or questions to be displayed.

plotrange

A vector of length 2 containing the plot boundaries within or over the score index interval c(0,100).

key

A integer vector of indices of right answers. If the data are rating scales, this can be NULL.

titlestr

A title string for plots.

saveplot

A logical value indicating whether the plot should be saved to a pdf file.

width

A vector of length 2 defining the lower and upper limits on the ordinate for the plots.

ttlsz

Title font size.

axisttl

Axis title font size.

axistxt

Axis text(tick label) font size.

lgdlab

Legend label font size.

Details

Sensitivity curves for each question indexed in the index argument. A request for a keystroke is made for each question.

Value

A list vector is returned which is of the length of argument plotindex. Each member of the vector is a gg or ggplot object for the associated plotindex value. Each plot can be displayed using the print command. The plots of item power are produced as a side value even if no output object is specified in the call to the function.

Author(s)

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

Power_plot, Entropy_plot, ICC_plot

Examples

#  Example 1.  Display the option sensitivity curves for the 
#  short SweSAT multiple choice test with 24 items and 1000 examinees.
dataList <- Quant_13B_problem_dataList
SfdList  <- Quant_13B_problem_parmList$SfdList
Qvec     <- Quant_13B_problem_parmList$Qvec
scrfine  <- seq(0,100,len=101)
oldpar   <- par(no.readonly=TRUE)
Sensitivity_plot(scrfine, SfdList, Qvec, dataList, plotindex=1)
par(oldpar)