NWEA’s RIT scale stands for Rasch UnIT scale. There are several RIT scales: one each for reading, language usage, mathematics, and general science plus a few scales that are under development.
What are the characteristics of the RIT scales?
These RIT scales are stable, equal interval scales that use individual item difficulty values to measure student achievement independent of grade level (that is, across grades). "Equal interval" means that the difference between scores is the same regardless of whether a student is at the top, bottom, or middle of the RIT scale. "Stable" means that the scores on the same scale from different students, or from the same students at different times, can be directly compared, even though different sets of test items are administered. A RIT score also has the same meaning regardless of the grade or age of the student.
In summary, the RIT scale is:
- An achievement scale
- Accurate
- Equal interval
- Useful for measuring growth over time
- The same regardless of the grade or age of the student
See also: How can I explain RIT scores to students and parents?
How was the RIT scale developed?
The theory governing scale construction is called Item Response Theory (IRT). NWEA uses a specific IRT model conceived by Danish mathematician Georg Rasch (1901-1980). Rasch is best known for his contributions to psychometrics, and his model is used extensively in assessment in education, particularly for skill attainment and cognitive assessments.
What does a particular RIT score mean?
A RIT score measures a student's level of achievement in a particular subject. If a student has a particular RIT score, this means that the student is about 50% likely to correctly answer an item calibrated at that RIT level.
NWEA reports contain normative data from our norms study that help put the RIT score into context by connecting RIT scores to achievement percentiles. You can find the percentile ranking for a particular RIT score on most reports, allowing you to compare a student's RIT score with other students in the same grade and subject.
For additional information about the RIT scale and norms, refer to:
How is the RIT level of a test item determined?
Each test question (or item) on a MAP Growth test is calibrated to the RIT scale, meaning that each item has its own calibrated RIT value.
Items are calibrated to our scale through embedded field testing. Every test event includes some new field test items at various points in the test. These items do not count towards a student’s score but serve as a way to collect at least 1,000 responses from a wide range of student abilities. From those responses we determine the point on our scale where students of a particular achievement level (their RIT) are answering the question correctly 50% of the time. For well-fitting items, that RIT value becomes the calibrated RIT of the item.
See also:
Sampling Error
Sampling error communicates information about the precision of a statistical estimate, such as a RIT score. A student's true RIT score is always an unknown because no measure can be constructed that provides a perfect reflection of that true RIT score.
For MAP Growth tests that use Rasch model as its item response theory (IRT) model, standard error of measurement (SEM) can be used to indicate the magnitude of sampling error for each individual MAP score level. That is, for each individual RIT score, there is an SEM expressing the level of estimation precision. This SEM can be used to generate the confidence interval of a RIT score, that is, a RIT range likely to include the true RIT score, to provide an estimate of the reliability of the observed RIT score.
For example, if a RIT range is calculated using RIT +/- SEM, then this RIT range indicates that if the student were retested repeatedly, the student's scores would fall within that range 68% of the time.
