IREFER= identifying items for recoding (with IVALUE=)

Responses are revalued according to the matching codes in IVALUE=. If this implies that the items may have different rating (or partial credit) scale structures, so ISGROUPS= may also be required.

IREFER= has three forms: IREFER=AABBCDAAD and IREFER=* list * and IREFER=*filename

Valid one-character IREFER= codes include: !#$%&-./123456789<>@ABCDEFGHIJKLMNOPQRSTUVWXYZ^_|~

A-Z are the same as a-z.

Characters with ASCII codes from 129-255 can also be used, but display peculiarly: ÎÏÐÑÒÓÔÕÖ×ØÙÚÛÜÝÞßàáâã etc.

When XWIDE=2 or more, then

either        (a) Use one character per XWIDE and blanks,

               NI=8

               XWIDE=2

               IREFER=' A B C D D C B A'

or        (b) Use one character per item with no blanks

               NI=8

               XWIDE=2

               RESCORE='ABCDDCBA'

Item identifying codes can be letters or numbers. "A" is the same as "a", etc.

Example 1.        There are 3 item types. Items are to rescored according to Type A and Type B. Other items to keep original scoring.

       CODES = 1234

       IREFER = AAAAAAAABBBBBBBB*******        3 item types: ("a" is the same as "A" in these codes)

       IVALUEA = 1223                Recode Type A items

       IVALUEB = 1123                Recode Type B items

       IVALUE* = 1234                Recode Type * item. Can be omitted

or

       IREFER=*

       1-8 A

       9-16 B

       17-23 *

       *

or

       IREFER=*filename.txt

in filename.txt:

       1-8 A

       9-16 B

       17-23 *

Example 2.        There are 3 item types. Responses are 2 characters wide. Items are to rescored according to Type A and Type B. Other items to keep original scoring.

       XWIDE=2

       CODES = '1 2 3 4 '

       IREFER = AAAAAAAABBBBBBBB*******        3 item types

       IVALUEA = '1 2 2 3 '                Recode Type A items

       IVALUEB = '1 1 2 3 '                Recode Type B items

       IVALUE* = 1234                Recode Type * item. Can be omitted

Example 3:        All items are to be rescored the same way

       NI = 100                        100 ITEMS

       IREFER=*

       1-100        X                        FOR ALL 100 ITEMS, reference is X

       *

       Codes        = 12345                rescore 12345

       IVALUEX = 12223                into 12223

Example 4:        Items are to be rescored in 3 different ways, and then the items are to be divided into 4 rating scale structures.

       ISGROUPS=11112223312444        ; 4 RATING SCALE GROUPINGS

       IREFER  =AAAABBBCCABBBB        ; 3 RECODINGS

       CODES   =01234        ; ORIGINAL CODES IN DATA

       IVALUEA =01234        ; ORIGINAL CODING MAINTAINED - THIS LINE CAN BE OMITTED

       IVALUEB =43210        ; CODING IS REVERSED

       IVALUEC =*112*        ; DICHOTOMIZED WITH EXTREME CATEGORIES MARKED MISSING

Example 5:        Multiple-choice test with 4 options, ABCD

       IREFER=ABCDDABADCDA        ; SCORING KEY

       CODES  =ABCD                ; VALID DATA CODES

       IVALUEA=1000                ; A SCORED 1

       IVALUEB=0100                ; B SCORED 1

       IVALUEC=0010                ; C SCORED 1

       IVALUED=0001                ; D SCORED 1

       MISSCORE=0                ; EVERYTHING ELSE IN THE DATA SCORED 0

Example 6:        A 10 item multiple choice test with 4 partial credit performance items scores 0,1,2,3.

       NI = 14                        ; 14 items

       ;        12345678901234

       ISGROUPS=DDDDDDDDDD0000        ; 10 Dichotomies in Group "D". 4 Partial Credit items each in its own group "0"

       IREFER  =ABCDDABADC1111        ; ITEM REFERENCE FOR THE 14 ITEMS

       CODES  =ABCD0123                ; VALID DATA CODES

       IVALUEA=10000000                ; A SCORED 1

       IVALUEB=01000000                ; B SCORED 1

       IVALUEC=00100000                ; C SCORED 1

       IVALUED=00010000                ; D SCORED 1

       IVALUE1=00000123                ; PERFORMANCE ITEMS: 0,1,2,3

       MISSING-SCORED=0                ; EVERYTHING ELSE IN THE DATA SCORED 0