CFILE= scored category label file

Rating (or partial credit) scale output is easier to understand when the categories are shown with their substantive meanings. Use CFILE= to label categories using their scored values, i.e., after rescoring. Use CLFILE= to label categories using their original codes, i.e., before any rescoring.

Labels for categories, after they have been scored, can be specified using CFILE= and a file name, or CFILE=* and placing the labels in the control file. Each category number is listed (one per line), followed by its descriptive label. If the observations have been rescored (NEWSCORE=) or keyed (KEYn=), then use the recoded category value in the CFILE= specification. When there are different category labels for different ISGROUPS= of items, specify an example item from the grouping, followed immediately by "+" and the category number. Blanks or commas can be used a separators between category numbers and labels.

Example 1:        Identify the three LFS categories, 0=Dislike, 1=Don't know, 2=Like.

CODES=012

CFILE=*

0 Dislike

1 Don't know

2 Like

*

The labels are shown in Table 3.2 as:

-------------------------------------------------------

CATEGORY OBSERVED AVGE  INFIT OUTFIT  STRUCTURE

 LABEL    COUNT   MEASURE MNSQ  MNSQ  MEASURE

-------------------------------------------------------

   0        378     -.87  1.08  1.19   NONE     Dislike

   1        620      .13   .85   .69     -.85   Don't know

   2        852     2.23  1.00  1.46      .85   Like

-------------------------------------------------------

Example 2:        Items 1-10 (Grouping 1) are "Strong Disagree, Disagree, Agree, Strongly Agree". Items 11-20 (Grouping 2) are "Never, Sometimes, Often, Always".

NI=20

CODES=1234

ISGROUPS=11111111112222222222

CFILE=*

7+1 Strongly Disagree        ; We could use any item number in Grouping 1, i.e., 1, 2, 3, 4, 5, 6, 7, 8, 9, 10

7+2 Disagree                ; item 7 has been chosen

7+3 Agree

7+4 Strong Agree

13+1 Never                ; We could use any item number in Grouping 2, i.e., 11, 12, 13, 14, 15, 16, 17, 18, 19, 20

13+2 Sometimes        ; item 13 has been chosen

13+3 Often

13+4 Always

*

Example 3:        To enter CFILE= information on the DOS Prompt or Extra Specifications lines, using commas instead of blanks as separators:

C:>WINSTEPS SF.TXT SFO.TXT CFILE=* 1,Dislike 2,Don't-know 3,Like *

Example 4:        Some items have one rating scale definition, but most items have another rating scale definition. But each item is calibrated with its own structure: ISGROUPS=0

NI=20

CODES=1234

ISGROUPS=0

CFILE=*

1 Strongly Disagree        This scale is used by most items

2 Disagree

3 Agree

4 Strong Agree

16+1 Never                16 is one item using the other scale

16+2 Sometimes

16+3 Often

16+4 Always

17+1 Never                17 is another item using the other scale

17+2 Sometimes

17+3 Often

17+4 Always

....                        for all the other items using the other scale

*

Example 5:        Several categories are collapsed into one category. The original codes are A-H. After rescoring there is only a dichotomy: 0, 1.

NI=30

CODES =ABCDEFGH

NEWSCORE=00011110

CFILE=*

0 Fail                Specify the categories as recoded

1 Pass

*