KEYn= scoring key

Usually only KEY1= is needed for an MCQ scoring key.


Up to 99 keys can be provided for scoring the response choices, with control variables KEY1= through KEY99=. Usually KEY1= is a character string of "correct" response choices. The standard is one column per correct response, or two columns if XWIDE=2.


As standard, responses matching the characters in KEY1= are scored 1. Other valid responses are scored 0. KEY2= through KEY99= are character strings of successively "more correct" response choices to be used when more than one level of correct response choice is possible for one or more items. The standard score value for KEY2= is 2, and so on up to the standard score value for KEY99= which is 99. The values assigned to these keys can be changed by means of KEYSCR=. If XWIDE=1, only the values assigned to KEY1= through KEY9= can be changed, KEY10= through KEY99= retain their standard values of 10 through 99. If XWIDE=2, the all KEYn= values can be changed.


More complicated scoring can be done with IREFER=


Example 1: A key for a 20-item multiple choice exam, in which the choices are coded "1", "2", "3" and "4", with one correct choice per item, scored 1. Wrong, invalid and missing responses are scored 0.

 CODES = 1234   ; valid codes

 KEY1  = 31432432143142314324 ; correct answers scored 1

 ; incorrect responses in CODES= automatically scored 0

 MISSING-SCORED = 0 ; scoring of responses not in CODES=


Example 2: A 20-item MCQ test with responses entered as "a", "b", "c", "d". Wrong responses scored 0. Invalid and missing responses are scored "not administered", and so excluded from the analysis

 CODES=abcd   ; valid responses

 KEY1 =cadcbdcbadcadbcadcbd ; ; correct answers scored 1

 ; incorrect responses in CODES= automatically scored 0

 MISSING-SCORED = -1 ; scoring of responses not in CODES= (default)


Example 3: A 20 item multiple choice exam with two somewhat correct response choices per item. One of the correct choices is "more" correct than the other choice for each item, so the "less correct" choice will get a score of "1" (using KEY1=) and the "more correct" choice will get a score of "2" (using KEY2=). All other response choices will be scored "0":

 CODES=1234   valid responses

 KEY1=23313141324134242113  assigns 1 to these responses

 KEY2=31432432143142314324  assigns 2 to these responses

 ;      0 is assigned to other valid responses

 ISGROUPS = 0 ; for the Partial Credit model

 MISSING-SCORED = 0 ; scoring of responses not in CODES=


Example 4: A 100 item multiple choice test key.




  +ACBCDADDCDBBADCDACBC ; continuation lines 


Example 5: Multiple score key for items 1 to 10. Items 11 to 15 are on a rating scale of 1 to 5

  CODES  = abcd12345

  KEY1   = bacdbaddcd*****

  RESCORE= 111111111100000 ; RESCORE= signals when to apply KEY1=

 ISGROUPS= 111111111122222 ; 1 indicates dichotomy, 2 indicates rating scale


Example 6: A 12 item test. Items 1-5 are MCQ with responses entered as "ABCD", with one of those being correct: Item 1, correct response is B. Item 2 is C. 3 is D. 4 is A. 5 is C. Then items 6-10 are partial-credit performance items rated 0-5. Items 11-12 are two dichotomous items, scored 0,1.

  CODES =ABCD012345 ; screen for all valid codes in the data file 

  KEY1 = BCDAC******* ; Key1= automatically has the value "1", etc.

RESCORE= 111110000000 ; "1" selects the KEY1=

ISGROUPS=111110000022 ; 1 indicates MCQ, 0 indicates partial credit, 2 indicates dichotomy


Example 7: Item 1 has correct options B,D,E. Other items have only one correct option.









KEY2 = D********

KEY3 = E********



Item 1

Item 2

Item 3

Item 4

Item 5

Item 6

Item 7

Item 8

Item 9



ADABADCCD Person 1  ; this scores as 001000000

BBDDDCAAB Person 2  ;         110100000

CDCCDBABA Person 3  ;         000001000

DCBCCACDC Person 4  ;         100010011

EDCDCDCBD Person 5  ;         100110000

Help for Winsteps Rasch Measurement Software: Author: John Michael Linacre

Facets Rasch measurement software. Buy for $149. & site licenses. Freeware student/evaluation download
Winsteps Rasch measurement software. Buy for $149. & site licenses. Freeware student/evaluation download

State-of-the-art : single-user and site licenses : free student/evaluation versions : download immediately : instructional PDFs : user forum : assistance by email : bugs fixed fast : free update eligibility : backwards compatible : money back if not satisfied
Rasch, Winsteps, Facets online Tutorials

Forum Rasch Measurement Forum to discuss any Rasch-related topic

To receive the monthly News Email about Winsteps and Facets,
enter your email address here:

I want to Subscribe: & click below
I want to Unsubscribe: & click below

Please set your SPAM filter to accept emails from welcomes your comments:

Your email address (if you want us to reply):


Rasch Publications
Rasch Measurement Transactions (free, online) Rasch Measurement research papers (free, online) Probabilistic Models for Some Intelligence and Attainment Tests, Georg Rasch Applying the Rasch Model 3rd. Ed., Bond & Fox Best Test Design, Wright & Stone
Rating Scale Analysis, Wright & Masters Introduction to Rasch Measurement, E. Smith & R. Smith Introduction to Many-Facet Rasch Measurement, Thomas Eckes Invariant Measurement: Using Rasch Models in the Social, Behavioral, and Health Sciences, George Engelhard, Jr. Statistical Analyses for Language Testers, Rita Green
Rasch Models: Foundations, Recent Developments, and Applications, Fischer & Molenaar Journal of Applied Measurement Rasch models for measurement, David Andrich Constructing Measures, Mark Wilson Rasch Analysis in the Human Sciences, Boone, Stave, Yale
in Spanish: Análisis de Rasch para todos, Agustín Tristán Mediciones, Posicionamientos y Diagnósticos Competitivos, Juan Ramón Oreja Rodríguez
Winsteps Tutorials Facets Tutorials Rasch Discussion Groups

Coming Rasch-related Events
Sept. 4 - Oct. 16, 2015, Fri.-Fri. On-line workshop: Rasch Applications, Part 1: How to Construct a Rasch Scale (W. Fisher),
Sept. 9-11, 2015, Wed.-Fri. In-person workshop: Introductory Rasch (A. Tennant, RUMM), Leeds, UK,
Sept. 14-16, 2015, Mon.-Wed. IACAT Conference: International Association of Computerized Adaptive Testing, Cambridge, UK,
Sept. 14-16, 2015, Mon.-Wed. In-person workshop: Intermediate Rasch (A. Tennant, RUMM), Leeds, UK,
Sept. 17-18, 2015, Thur.-Fri. In-person workshop: Advanced Rasch (A. Tennant, RUMM), Leeds, UK,
Sept. 30 - Oct. 2, 2015, Wed.-Fri. In-person workshop: IRT and Rasch analyses using R and Concerto (C. Gibbons), Cambridge, UK,
Oct. 16 - Nov. 13, 2015, Fri.-Fri. On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps),
Oct. 23 - Nov. 20, 2015, Fri.-Fri. On-line workshop: Rasch Applications, Part 2: Clinical Assessment, Survey Research, and Educational Measurement (W. Fisher),
Nov. 13, 2015, Fri. In-person workshop: Rasch Models in Business Administration, in Homage to Professor Pedro Álvarez-Martínez, Tenerife, Canary Islands,
Dec. 2-4, 2015, Wed.-Fri. In-person workshop: Introductory Rasch (A. Tennant, RUMM), Leeds, UK,
March 18, 2016, Fri. UK Rasch User Group Meeting, Durham, UK,
March 23-24, 2016, Wed.-Thur. In-person workshop: Introduction to Rasch using Winsteps (W.Boone), Cincinnati OH,
April 8-12, 2016, Fri.-Tues. AERA Annual Meeting, Washington DC,
Aug. 12 - Sept. 9, 2016, Fri.-Fri. On-line workshop: Many-Facet Rasch Measurement (E. Smith, Facets),
The HTML to add "Coming Rasch-related Events" to your webpage is:
<script type="text/javascript" src=""></script>