Positively-oriented facet = 1 |
This is for 32-bit Facets 3.87. Here is Help for 64-bit Facets 4
This command specifies which facets are positively oriented. The standard in Facets is for only the first facet to be measured positively, so consult the table below to understand how to interpret the Rasch measures which are output by Facets. The facet orientations specified in your command file are indicated in the output on the all-facet ruler (Table 6.0) with a + or - sign at the top of the ruler. (This section incorporates text from William Bonk.)
If both Positive= and Negative= are specified, only the first one encountered is actioned.
Example 1: Positive=1 (Only facet 1 is positively-oriented. Facets uses this as standard)
Persons (facet 1) respond to items (facet 2) which are scored by raters using rating scales (facet 3). Persons are measured positively, i.e., a high ability measure means the raw score was high, a low measure means the raw score was low. On the other hand, items are measured negatively so the higher the Rasch measure, the greater difficulty of the item; so are raters, such that the higher the Rasch measure, the greater severity of the rater. This is a convention in educational measurement.
Facet |
Interpretation |
Examinee (positive) |
Higher Rasch measures mean greater ability |
Test items (negative) |
Higher Rasch measures mean items are harder |
Survey items (negative) |
Higher Rasch measures mean items are more difficult to endorse |
Raters (negative) |
For examinees: Higher Rasch measures mean raters are more severeFor standard-setting: Higher Rasch measures mean raters are less demanding |
Prompt (negative) |
Higher Rasch measures mean prompts are harder (tend to yield lower raw scores) |
Example 2: Positive=1,2,3 (All facets are positively-oriented)
Another method is to orient all facets positively. For instance, Patients (facet 1) are rated on tasks (facet 2) by raters (facet 3). All facets are measured positively, so that higher Rasch measures mean that patients scored higher, that tasks were easier, and that raters were more lenient. This is the convention in health care measurement.
Positive=1,2,3
Facet |
Interpretation |
Examinee (positive) |
Higher Rasch measures mean greater ability |
Test items (positive) |
Higher Rasch measures mean items are easier |
Survey items (positive) |
Higher Rasch measures mean items are easier to endorse |
Raters (positive) |
For examinees: Higher Rasch measures mean raters are more lenientFor standard-setting: Higher Rasch measures mean raters are more demanding |
Prompt (positive) |
Higher Rasch measures mean prompts are easier (tend to yield higher raw scores) |
Positive= specifies which facets are to be measured positively, i.e., higher score means higher logit value. The other facets will be negatively oriented. Positively-oriented facets are indicated by "+" in Table 6.0. Positive-orientation and Negative-orientation" are complex. We must answer:
For a particular facet,
Do increasing raw scores indicate more or less of what we are looking for?
counting right answers = more capability
counting mistakes = less capability
longer times in performing a task = less capability
higher Likert rating = more agreement or less agreement (depending how the categories are numbered).
higher p-value = more easiness for items
higher ratings = more leniency for raters
etc.
For a particular facet,
Do we want higher Rasch measures to indicate higher or lower levels of what we are looking for:
more ability as in educational testing
more disability as in some medical applications
more leniency for raters
more severity for raters
more difficulty (to perform, to answer correctly, to agree with, etc.) for items
more easiness (to perform, to answer correctly, to agree with, etc.) for items
or
etc.
Then, for a particular facet,
if higher raw scores align with what we want higher Rasch measures to indicate, then the facet must be coded as "Positive=",
but if lower raw scores align with what we want higher Rasch measures to indicate, then the facet must be omitted from "Positive=".
Orientation of facet |
||
Meaning of raw scores |
Positive |
Negative |
Examinees: higher raw score indicate higher capability |
Higher Rasch measures mean greater ability |
Higher Rasch measures mean greater disability (not recommended because tends to be misunderstood) |
Items: higher p-values or average ratings indicate greater easiness |
Higher Rasch measures mean greater item easiness |
Higher Rasch measures mean greater item difficulty |
Raters: higher average ratings indicate greater leniency for examinees or more demanding for standard setting |
Higher Rasch measures mean greater rater leniency or more demanding for standard setting |
Higher Rasch measures mean greater rater severity or less demanding for standard setting |
Prompt: higher average raw scores indicate greater easiness |
Higher Rasch measures mean greater prompt easiness |
Higher Rasch measures mean greater prompt difficulty |
Example 3: The usual convention in educational testing is that only those facets corresponding to the objects of measurement, typically persons, are measured positively (higher score means higher ability measure), but the agents of measurement, items, tasks and judges are measured negatively (lower score means higher difficulty measure or higher severity measure). For instance, Persons (facet 1) take items (facet 2) with some items rated by raters (facet 3). Persons are to be measured positively, i.e., higher score corresponds to higher ability measure. Items are to be measured negatively (lower score corresponds to higher difficulty measure) and raters are to be measured negatively (lower score corresponds to higher severity).
Positive=1
Example 4: In Example 3, the raters (facet 3) are to be reported by leniency (higher score means higher leniency measure), not by severity (lower score means higher severity measure).
Positive=1,3
Example 4: The usual convention in healthcare is that all facets corresponding are measured positively: higher score means higher ability measure, higher easiness measure or higher leniency measure. For instance, Patients (facet 1) are rated on items (facet 2) by raters (facet 3). All facets are to be measured positively, i.e., higher score corresponds to higher measure.
Positive=1,2,3
Example 5: Both facet 2, boys, and facet 4, girls, are to be reported as positively oriented (higher scores = higher measures). All other facets negatively (higher scores = lower measures):
Positive=2,4
Example 6: No facets are to be positively oriented. For all facets, higher scores mean less of what we are looking for.
Positive=
Help for Facets 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