The output file name can be entered at the prompt when Facets starts, or be entered as part of the specification file.
The name of the file that will contain the main results of the analysis is the first entry. This is the name of file into which output is written, e.g.,
Output = results.txt
An output file name given on the DOS command line supersedes the results file name given here, e.g, C:>FACETS SPECS.txt OUTPUT.txt, causes output to go to OUTPUT.txt rather than RESULTSOUT.txt. If two files names are given on the DOS line, they are output and anchor files, three names are the output, anchor and residual files.
The anchor output file name for a file of anchoring values is the second entry (or specified with Anchorfile=. Whenever a file name is given, then Facets writes out a new specification file containing the input specifications for this analysis. This file omits any specifications entered on the DOS command line, but includes the final estimated measures for all elements and scales. This file also has all estimated measures marked as ",A" for "anchored".
These anchor values can be used as starting values for slightly different later runs. Edit the ",A"'s out of the first line of each facet in the Labels= specifications and out of the category lines of Rating scale=.
The residual output file name for a file of observations, their expected values and their residuals is the third entry, or specified with Residualfile=. Whenever a file name is given, the standardized residuals for all the data points will be written to it.
Example 1: A file of anchor values is to be produced to be used in an equating study. This file is to be named "Anchor.txt":
Output = Results.txt,Anchor.txt
or
Outputfile = Results.txt
Anchorfile = Anchor.txt
or
C:>Facets SPECS.txt Results.txt Anchor.txt
Example 2: A file of residual values is needed for fit analysis, but no anchored file is wanted.
Output = Results.txt, ,Residual.txt ; Note: ", ," means no anchor output file
or
Outputfile = Results.txt
Residualfile = Residual.txt
