RESCORE= response recoding (with NEWSCORE= or KEYn=) |
The responses in your data file may not be coded as you desire. The responses to some or all of the items can be rescored or keyed using RESCORE=. RESCORE= and NEWSCORE= are ignored when KEYn= is specified, except as below. If rescoring implies that the items have different rating (or partial credit) scale structures, ISGROUPS= may also be required.
RESCORE= *file name |
file containing details |
RESCORE = * |
in-line list |
RESCORE = codes |
codes for item groups |
RESCORE= has three forms: RESCORE=1101110 and RESCORE=* list * and RESCORE=*filename
RESCORE=" " or 2 or is omitted
All items are recoded using NEWSCORE=. RESCORE=2 is the standard when NEWSCORE= is specified.
RESCORE= some combination of 1's and 0's
Only items corresponding to 1's are recoded with NEWSCORE= or scored with KEYn=. When KEYn is specified, NEWSCORE= is ignored.
If some, but not all, items are to be recoded or keyed, assign a character string to RESCORE= in which "1" means "recode (key) the item", and "0" (or blank) means "do not recode (key) the item". The position of the "0" or "1" in the RESCORE= string must match the position of the item-response in the item-string.
When XWIDE=2 or more, then
either (a) Use one character per XWIDE and blanks,
NI=8
XWIDE=2
RESCORE=' 1 0 1 0 1 0 1 1'
or (b) Use one character per item with no blanks
NI=8
XWIDE=2
RESCORE='10101011'
Example 1: The original codes are "0" and "1". You want to reverse these codes, i.e., 1 0 and 0 1, for all items.
XWIDE=1 one character wide responses (the standard)
CODES =01 valid response codes are 0 and 1 (the standard)
NEWSCORE=10 desired response scoring
RESCORE=2 rescore all items - this line can be omitted
Example 2: Your data is coded "0" and "1". This is correct for all 10 items except for items 1 and 7 which have the reverse meaning, i.e. 1 0 and 0 1.
NI=10 ten items
CODES =01 standard, shown here for clarity
(a) old method - which still works:
NEWSCORE=10 revised scoring
RESCORE=1000001000 only for items 1 and 7
or
NEWSCORE=20
RESCORE=*
1 1 item 1 is to be rescored
7 1 item 7 is to be rescored
*
(b) new method - recommended:
IVALUE1 =10 revised scoring
IVALUE0 =01 scoring unchanged, so this line can be omitted.
IREFER =1000001000 only for items 1 and 7
If XWIDE=2, use one or two columns per RESCORE= code, e.g., " 1" or "1 " mean recode (key). " 0" or "0 " mean do not recode (key).
Example 3: The original codes are " 0" and " 1". You want to reverse these codes, i.e., 1 0 and 0 1, for items 1 and 7 of a ten item test.
NI =10 ; ten items
XWIDE =2 ; two characters wide
CODES =" 0 1" ; original codes
NEWSCORE=" 1 0" ; new values
RESCORE =" 1 0 0 0 0 0 1 0 0 0" ; rescore items 1 & 7
Example 4: The original codes are "0", "1", and "2". You want 0 0, 1 1, and 2 1 for all items
XWIDE=1 one character wide (standard)
CODES =012 valid codes
NEWSCORE=011 desired scoring
Example 5: The original codes are "0", "1", and "2". You want to make 0 2, 1 1, and 2 0, for even-numbered items in a twenty item test.
NI=20 twenty items
CODES =012 three valid codes
NEWSCORE=210 desired scoring
RESCORE=01010101010101010101 rescore "even" items
Example 6: The original codes are "0", "1", "2", "3" and some others. You want to make all non-specified codes into "0", but to treat codes of "2" as missing.
CODES = 0123 four valid codes
NEWSCORE= 01X3 response code 2 will be ignored
MISSCORE=0 treat all invalid codes as 0
Example 7: The original codes are "0", "1", "2", "3". You want to rescore some items selectively using KEY1= and KEY2= and to leave the others unchanged - their data codes will be their rating values. For items 5 and 6, 0 0, 1 0, 2 1, 3 2; for item 7, 0 0, 1 0, 2 0, 3 1. Responses to other items are already entered correctly as 0, 1, 2, or 3.
CODES =0123 valid codes
RESCORE=0000111000 rescore items 5,6,7
KEY1 =****223*** keyed for selected items
KEY2 =****33X*** the X will be ignored
^ read these columns vertically
Example 8: 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=
Help for Winsteps Rasch Measurement and Rasch Analysis Software: www.winsteps.com. Author: John Michael Linacre
Facets Rasch measurement software.
Buy for $149. & site licenses.
Freeware student/evaluation Minifac download Winsteps Rasch measurement software. Buy for $149. & site licenses. Freeware student/evaluation Ministep download |
---|
Forum: | Rasch Measurement Forum to discuss any Rasch-related topic |
---|
Questions, Suggestions? Want to update Winsteps or Facets? Please email Mike Linacre, author of Winsteps mike@winsteps.com |
---|
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 |
---|
Coming Rasch-related Events: Winsteps and Facets | |
---|---|
Oct 21 - 22 2024, Mon.-Tues. | In person workshop: Facets and Winsteps in expert judgement test validity - UNAM (México) y Universidad Católica de Colombia. capardo@ucatolica.edu.co, benildegar@gmail.com |
Oct. 4 - Nov. 8, 2024, Fri.-Fri. | On-line workshop: Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com |
Jan. 17 - Feb. 21, 2025, Fri.-Fri. | On-line workshop: Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com |
May 16 - June 20, 2025, Fri.-Fri. | On-line workshop: Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com |
June 20 - July 18, 2025, Fri.-Fri. | On-line workshop: Rasch Measurement - Further Topics (E. Smith, Facets), www.statistics.com |
Oct. 3 - Nov. 7, 2025, Fri.-Fri. | On-line workshop: Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com |
Our current URL is www.winsteps.com
Winsteps® is a registered trademark