Statistical and psychometric utilities

for psychotherapy and counselling research

Information written and mounted by Chris Evans (Email to: http://www.psyctc.org/cgi-bin/mailto.pl?webmaster) on 17.vi.95, last updated 20.ix.07

New as of 20.ix.07

• Program to generate all nC2 pairs from n objects for n < 33
• Program to generate various extensions of kappa for multiple raters in inter-rater reliability studies

New as of 18.xi.04

New as of 2.ii.04:

Not so new!

• Probably the most important information here is that about the CORE (Clinical Outcomes in Routine Evaluation) system That's not very statistical as yet but some of the information in there, particularly the powerpoint presentations, do have statistical aspects. Mounted 17.viii.03
• Similarly important on theoretical grounds (I think!) is my work on probabilities for matching scores "derangements" This is a very simple method of demonstrating the statistical significance of information transfer through idiographic techniques. Mounted 25.v.01, updated 21.xii.03
• Then there's information about determining reliable and clinically significant change Mounted 31.v.2001, tweaked several times in 2003, latest 21.xii.03
• Finally in the top rank of my statistical utilties are my interactive calculators for confidence intervals of any required spread (95% or other):
  • confidence interval of a proportion Mounted 12.viii.03
  • confidence interval of a difference between two (independent) proportions Mounted 14.viii.03
  • confidence interval of a mean from mean, s.d. (or s.e.) and n Mounted 16.viii.03, last updated 22.xii.03
• Then there's the issue of "internal reliability" or "internal consistency" which I think is very much avoided to the huge detriment of much psychological and psychiatric research. I've mounted some programs:
  • feldt1.sas {1kb} for a single value (somewhat less necessary than it was now that you can get this from SPSS RELIABILITY as the CI of the "two-way mixed, consistency" ICC)
  • feldt1.ssc similar program for S+ (and probably fine in R too)
  • feldt1-table.ssc silly little extension of the above to deal with tables of alphas easily
  • feldt2.sas {1kb} which compares two values for independent samples and the same number of items (number of participants can be different)
  • feldt2.ssc similar program for S+/R
  • feldt3b.sas {2kb} which will accept a listing of pairs of values to be compared
• Then we're down to something I really must come back to develop more some time: repertory grids:
  • my SAS/IML program to do an INGRID style analysis of a repertory grid along the lines of the famous program written by the late Patrick Slater
  • similar S+ program (I'll try to fix up an interactive version some time)
• Then we're down to a rather random collection of programs I wrote because I couldn't find them elsewhere:
  • interactive random permutation generator (1). This calls a perl script random1.prl which takes the lowest and highest number of sequential numbers you want permuted, and a seed, and returns those numbers permuted. E.g. if you ask for numbers between 10 and 18 to be permuted, with a seed of 89 you will get: 13 12 10 16 11 18 15 17 14. Another seed would give you another sequence. Uses the perl rand function. I'd guess it's the same as the typical C function but don't know more! As ever, NO liability accepted!!
  • spreadsheet templates for plotting receiver operating characteristics (ROCs or R.O.C.s!; very simple I'm afraid)
  • trite SAS program to generate confidence intervals of means from output from SPSS DESCRIPTIVES!
  • SAS/IML program gives the probability and cumulative probabilities of r significant results from n tests under the (generally rather implausible) general null hypothesis. Crude but can handle large n which simpler implementations in MathCAD 6 which I was using at the time wouldn't where they produced overflow errors, leastways, they did back then. mounted 16.iii.98

• PSYCTC.org main site entry pages
• PSYCTC.org privacy policy