Skip to main content
. Author manuscript; available in PMC: 2010 Aug 12.
Published in final edited form as: Spine (Phila Pa 1976). 2009 Jul 15;34(16):1722–1731. doi: 10.1097/BRS.0b013e3181a8faf2

Figure 2.

Figure 2

Summary of Standard Errors of Measurement using the classical test theory survey-level (se-GL) and conditioned on score-level (se-SL) and the item response theory (se-IRT) response-level Estimation defined as the inverse of the test characteristic curve.

Note 1. The differences in the se-SL and se-IRT differences in the middle of the distribution are much smaller than these differences at the extreme scores.

Note 2. The shaded areas reflect the score levels were the measurement error tolerances are different.