Builds a PARSCALE data file and command file, executes the command file, and displays PARSCALE output in the Stata results window
-------------------------------------------------------------------------------
runparscale varlist , ID(subject id) [ RUnname(string) minsize(interger 20) display(string with 0,1,2 and/or 3) SCale(string 1.7) NQpt(string 11) CYcles(string 1000) cleanup ]
Required commands
varlist - Variables to be used in the PARSCALE run.
ID - a unique identifier for each record must be provided. This is used to merge in theta scores estimated from the PARSCALE run.
Options
runname(string) - file name stub used to name PARSCALE data and command files created by runparscale.
minsize(integer) - Enter the minimum category frequency allowed. The default value is 5% of the total number of observations in the last item on the varlist, or 20, whichever is smaller. Categories will be combined, if possible, to meet the minsize. Any variable that does not have enough observations in at least 2 categories will be dropped. If you do not want any categories combined, specify minsize(1).
display(string with 0,1,2 and/or 3) - displays the results of PARSCALE run phase 0, 1 2 or 3 as indicated. Any string that contains 0,1,2,3 will work (e.g., "0123" or "0,1,2,3" or "phase2only", or "phase 1 and 2", or "2").
scale - changes the scale parameter from the default of 1.7.
nqpt - changes the number of quadrature points from a default of 11.
cycles - changes the maximun number of iterations in PARSCALE stage 2 from the default of 1000.
cleanup - removes interim files, PARSCALE command, data and results files. If runname is not specified, cleanup is automatically invoked.
Description
runparscale brings the IRT analysis framework of PARSCALE into the Stata enviroment. While runparscale does little more than data reformat and ascii file creation, it removes a lot of the hassle of estimating IRT models.
Remarks
Program is rclass, returning item parameters and standard errors.
Warning message for variables with more than 15 levels (PARSCALE will reject). Letter codes automatically made for 2-digit values.
Items can have 2-10 categories. The program will run correctly with up to 15 categories (PARSCALE's maximum), but not all item cutpoints will be displayed. They will still be available in the runname.par file.
The maximum number of items is 230.
Allows missing values.
Allows character or numeric ID's up to 9 digits. Creates a numeric, 10-digit ID code for PARSCALE by adding 1,000,000,000 to the ID, first converting string IDs to a unique number if needed.
Please make sure that Stata's current working directory is the same as your data's directory (help cd).
Default PARSCALE instructions are:
>CALIB GRADED, LOGISTIC, SCALE=1.7, NQPT=11, CYCLES=1000, CRIT=.001
>SCORE EAP
If you want to change anything but the scale, nqpt, and cycles, you can edit the .PSL file or this program before running it.
Written for Stata 8.2.
Examples
. runparscale y1-y7, id(id) scale(1.83) display(2) runname(splunge)
. runparscale y1-y7, id(id) scale(1.83) display(2) cleanup
Authors
runparscale was written by Laura Gibbons, PhD and Richard Jones, ScD, under the direction of Paul Crane, MD MPH. We appreciate the assistance of Tom Koepsell, MD MPH.
Please see runparscale.ado for UW License information.
Laura Gibbons, PhD gibbonsl@u.washington.edu
Richard N Jones, ScD jones@mail.hrca.harvard.edu
Also see
difwithpar and prepar.