Error codes and their explanation

For Windows-related and other problems, see


If you need further help or to report bugs in Facets, please email Mike Linacre, author of Winsteps: mike \at/






"Specification=value" expected

A specification whose first one or two letters is not in the "INDEX OF Facets SPECIFICATIONS" was given.

If this message appears for line 1, then the specification file may not be in the correct format. Open the specification file with Microsoft Word, then save as "DOS text with line breaks".


Number invalid or greater than ___

Integers are usually in range 1 to 2147483647. Facet numbers are integers in the range 1 to 255. Facet 0 can be used to indicate that no facet applies.


Duplicate category label

A category number has been defined twice in a Rating (or partial credit) scale= specification.


More than ___ components in Model= statement

Each Model= statement has as many facet control characters, e.g., "?", as there are facets in the Facets= statement, then a scale character, e.g., "R", followed optionally by a weight, e.g., "1". You specified too many components.


Invalid or undefined scale

The Model= or Rating Scale= statement specified a scale type, e.g., "S", which is neither a scale type itself, e.g., "R", nor defined by "Rating Scale=S".


Duplicate Rating (or partial credit) scale= identifying labels

Two Rating (or partial credit) scale= specifications have the same scale name, e.g., "quality" in

"Rating (or partial credit) scale=quality"

and then again later,

"Rating (or partial credit) scale=quality"


Facets= statement conflicts with prior facet commands

Specify your one Facets= statement before other facet-related commands, such as "Positive=2" to prevent incorrect standard values being used.


Facet number out of range: 1-(number of Facets specified in Facets=)


All Model= statements must include ____ facet locations + type [+ weight]

Each model statement has as many facet control characters, e.g., "?", as there are facets, followed by a scale character, e.g., "R", followed optionally by a weight, e.g., "1". You specified too few components.


Category is not an integer in range 0 to 255

Valid responses are in the range 0 to 255, after recoding if specified.


Labels= contains the same facet twice

After a Labels= statement, the facets can be in any order, but each facet number can only be used once, e.g.,


3=facet 3

1=element 1 facet 3


1=facet 1

1=element 1 facet 1


3=facet 3 <- this is invalid. The facet is repeated!


Invalid category in Rating (or partial credit) scale= specification

Category values must be integers in the range 0 to 32767, or negative numbers, if they are to be treated as missing.


Extra term on DOS command line

The DOS command line can have

C:>FACETS SPECFILE [OUTFILE [ANCFILE]] Specification=Value .....

[ ] mean "optional".

Your DOS command line does not follow this scheme. Are there blanks before or after "=" signs?


This specification not permitted on DOS command line

You have specified something on the command line that Facets does not allowed there, e.g., Labels=, Model=, Rating (or partial credit) scale=


Models= problem


No element numbers specified after Labels=

Your Labels= command was not followed by a facet number, then element numbers, then "*", e.g., a correct specification is:


 1, Facet 1 name ; facet number

 21=One element ; element in first facet

 32=Another element

 * ; end of element list for this facet

 2, Facet 2 name

 1=Element one name



Sort length error - contact

Internal failure in Facets. Contact us prepared to give details of your specification file.

You can run probably produce useful output from Facets:

1) Remove any Arrange= specification

2) Specify "Vertical=no"


Non-numeric datum treated as missing

An observation is specified with a non-numeric values. It is ignored as missing data.


Invalid element number. Must be integers in the range 0 - 2147483646

0 is the null element number, unless Keepasnull= sets a different element number as the null element.

Please reassign element numbers greater than 2,147,483,646 to smaller unused element numbers. Delements=B allows larger element numbers to be used as element numbers in the data, provided that they are also the element labels. If you really have more than 2 billion elements in a facet, then you will need a custom version of Facets.


Invalid group number

Group numbers must be integers in the range 1 to 255


Invalid Model= statement

You did not use a valid facet control character, such as "?", or "#", a valid element number or a valid element-number range.


Invalid response value: non-numeric or too big for model

A response in this data line did not match the Model= or Rating (or partial credit) scale= specification.


Data record does not contain ___ facet references + data

You did not specify enough facet element references, or data elements in your data line.


Non-Integer value where integer expected

Element and category numbers must be integers, not real numbers like 2.5


Only one facet may have a range (-) in a data line

With 2 facets, "1-3,2-3, 1,0,1,0,1,1" is invalid. Enter:

1-3,2, 1,0,1

1-3,3, 1,1,0


Not enough responses for the range: expected: ___

You specified a range of elements, but did not provide one response for each element of the range, e.g., with two facets, "1-3,4,  2, 1" requires one more response, e.g., "1-3,4,  2, 1, 2".


Too many responses: expected: ______

You specified a range of elements, but provided more responses than there were elements in the range, e.g., with two facets, "1-3,4, 2, 1, 2, 2" has one response too many. Also check Dvalues=, if used.


Valid arrangements are facet number (optional) then A,F,M,N,P,a,m,f,n,p

Did you specify some other letter or a non-alphabetic character? Valid arrangements look like: "Arrange=Af,Mp,3M"


Data file error


Please specify Facets= before this specification

This specification requires a Facets= specification to precede it, e.g., Facets=3.


No usable data. Use Query=Y to check Models= and Labels=

No data match model statements, and reference specified elements, and have valid data values. Query=Y to discover the reason Facets rejected each datum.

F35 may be because there is only one observation for each element.

Here is a way to get your analysis to run ....

1. Put all the data in twice: copy-and-paste the current data after itself.

2. Weight the data 0.5

Models= ?, ?, ?, R, 0.5


Error F36: All data eliminated as extreme.  Dropped elements - first: facet (facet number) element (element number) "(element label)" - last: facet (facet number) element (element number) "(element label)"

Extreme scores (zero or perfect) correspond to infinite measures and so provide no useful information about the measures of other elements. Therefore, data included in extreme scores are eliminated from the main estimation process. All scores were extreme, so all data were eliminated. Here are some possibilities:

1) not enough data

2) data entry errors

3) the data are not zeroes or positive integers. Other values can be processed with Rating Scale=

4) the model specified in Models= does not match the data.

5) the data have a Guttman pattern. On first analysis, there are some extreme scores for persons, items, judges, tasks, etc. So these are dropped from immediate estimation. Then, in the remaining data, there are some extreme scores. These are dropped. The process continues until no data are left.


Incompatible file usage: ______

The same file name has been specified for two different files, e.g., a data file and an output file. Rerun Facets with amended file names.


Lsort sequence error

This is an internal sorting error within Facets. Please contact :


Umean= must be specified before Labels= and Rating=

User rescaling must be specified in the specification file before any lines to which it applies. Place Facets= and Umean= early in your specification file.


Data= not specified

Data= must be followed by the observations, or be Data= filename.


No file name

A file name is expected in this specification.


File name contains * or ?, or ends with \ / or :

File name does not accord with Windows rules.


File not found

Specified input file does not exist.


Invalid line-end format: only LF code, CR-LF expected

File is not in MS-DOS text with line breaks format. Read it into Word (or such like) and then "Save As" in "DOS text with line breaks" format


Entered= references do not match ________

Entered= specification not compatible with Facets= specification.


File has no contents

Empty input file not allowed.


Invalid line-end format: only CR code, CR-LF expected.

File is not in MS-DOS text with line breaks format. Read it into Word (or such like) and then "Save As" in "DOS text with line breaks" format


Anchor value too extreme

Anchor value set outside the range of the floating-point processor.


Missing quote " in command line

There are unbalanced " " on the DOS command line


Work file problem

Rerun the analysis. If it still occurs, please contact


Execution canceled at user request

Execution canceled - perhaps from the Files pull-down menu.


File not found in batch mode

Specified input file does not exist. Specifying complete paths may solve this.


Too many Models= specified

More than 32,000 Models= specifications have been given.


Dvalues= must be facet, value e.g., 3,1-4 or facet, facet, start, length, e.g., 3,2,6,2

Check Dvalues= for format and validity.


Required file not found

A specified input file does not exist. Provide complete pathname.


Excel-related error

Facets may not be compatible with your version of Excel.


Field start or length problem in Dvalues=

See the Dvalues= instructions.


Non-numeric weight in Model= specification: "____"

Model= weights can omitted (and assumed to be 1) or specified with numeric values.


Reordered category value not positive integer or zero

Rating scale= reordered-value is incorrect. An anchor file may not have the correct format


No active element numbers: Models= and Labels=

Models= has selected no active element combinations, or Labels= contains no active elements.


Module (module.exe) not found. Facets is not installed correctly.

Reinstall Facets or copy the module from another folder.


SPSS file creation failed

Does the version of winspssg.exe match the version of Facets.exe?


Glabel= specification is missing a parameter value


Dvalues= references a data facet that is not defined, see Entered=


Too many fields on a line. The maximum is 256. Please divide the line into two lines. This may be caused by a non-standard end-of-line code.


Dvalues= reference, target relationship is too complex


Element range problem: Rating Scale= recode range not numeric. Should be number-number


Labels= appears twice


Facet number zero or negative


No valid elements found


Too many elements ( nnnn ) specified in Labels=

The list of elements has overflowed program memory. Please specify fewer elements.


Invalid target element number in this element specification

The target element number must be the number of another valid element


Target element numbers circular or nested too deep

Target element numbers reference elements with target reference numbers in a circle or with more than 10 in a chain.


Keepasnull= value out of range: -1 to 2147483647


Data= problem: too many elements ( nnnn ) specified in: aaaa-bbbb

If aaaa-bbbb is an element label, then specify Delements= facet-numberL, or disambiguate with a leading letter: Xaaaa-bbbb


Invalid element number. Delements=N. Must be integers in the range 0 - 2147483647

If the element number is an element label, please specify Delements=LN or Delements=L


Too many fields on a line. The maximum is 256. Please divide the line into two lines. This may be caused by a non-standard end-of-line code.


SPSS Interface: Input work file incorrect

There is a mismatch between Facets components, please contact

Internal error in winspssg.exe - perhaps it does not match Facets.exe


Windows-reported file problems. These are all filename or file availability problems.


Bad file name or number


File not found (53 not shown)


Bad file mode


File already open


Device I/O error


File already exists


Disk full


Too many files


Device unavailable


Permission denied


Disk not ready


Path/File access error


Path not found


Workfile failure.

In your autoexec.bat file, SET TEMP= or SET TMP= are missing or point to invalid paths. Try:



Facets runs under Windows-XP, but may initially fail due to Windows-XP not correctly setting up its temporary file folder. If you get a message like:

"Workfile failure 76 path is not found. for:C:\Document\Locals\Temp\"

then right-click on "My Computer"

select "Properties | Advanced | Environment Variables"

edit the User Environment variable called TMP to be C:\TEMP

Create a new folder C:\TEMP if you do not already have one.

Help for Facets Rasch Measurement Software: Author: John Michael Linacre.

For more information, contact or use the Contact Form

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

Click here to add your email address to the Winsteps and Facets email list for notifications.

Click here to ask a question or make a suggestion about Winsteps and Facets software.

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 with Raters and Rating Scales: Rasch Models for Rater-Mediated Assessments, George Engelhard, Jr. & Stefanie Wind 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
April 10-12, 2018, Tues.-Thurs. Rasch Conference: IOMW, New York, NY,
April 13-17, 2018, Fri.-Tues. AERA, New York, NY,
May 22 - 24, 2018, Tues.-Thur. EALTA 2018 pre-conference workshop (Introduction to Rasch measurement using WINSTEPS and FACETS, Thomas Eckes & Frank Weiss-Motz),
May 25 - June 22, 2018, Fri.-Fri. On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps),
June 27 - 29, 2018, Wed.-Fri. Measurement at the Crossroads: History, philosophy and sociology of measurement, Paris, France.,
June 29 - July 27, 2018, Fri.-Fri. On-line workshop: Practical Rasch Measurement - Further Topics (E. Smith, Winsteps),
July 25 - July 27, 2018, Wed.-Fri. Pacific-Rim Objective Measurement Symposium (PROMS), (Preconference workshops July 23-24, 2018) Fudan University, Shanghai, China "Applying Rasch Measurement in Language Assessment and across the Human Sciences"
Aug. 10 - Sept. 7, 2018, Fri.-Fri. On-line workshop: Many-Facet Rasch Measurement (E. Smith, Facets),
Sept. 3 - 6, 2018, Mon.-Thurs. IMEKO World Congress, Belfast, Northern Ireland
Oct. 12 - Nov. 9, 2018, Fri.-Fri. On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps),



Our current URL is

Winsteps® is a registered trademark

Mike L.'s Wellness Report: Effective weight loss program? The Mediterranean Diet, especially the M3 version