Test-Retest Reliability

Authors
Affiliations

Doctor of Physical Therapy

B.S. in Kinesiology

Doctor of Physical Therapy

B.A. in Neuroscience

Test-Retest reliability reflects the variation in measurements taken by an instrument on the same subject under the same conditions. In other words, Test-Retest reliability quantifies the similarity of scores when a study participant completes a test at 2 separate instances.

Interpretation

If this test was reliable, we would expect the 2 scores to be similar, if not identical, on both occasions (assuming that the person has not changed in the interim).

What if my scale has low Test-Retest Reliability?
  • A self administered scale with poor test-retest reliability cannot be changed without altering psychometric validity
  • A clinician-administered scale can be slightly changed by insuring that the instructions are clear and understood by the participant

Duration Between Tests

  • When assessing test-retest reliability, the length of time between time 1 and 2 creates an issue since there is a fine balance the researchers must find with time since there is trade-off between 2 competing requirements.

Too Short

  • If the duration is too short, the participants will answer the questionnaire by memory in order to appear consistent.

Too Long

  • If the duration is too long, the person’s mood, anxiety, symptoms, or whatever we are measuring could change.
  • The usual testretest interval is about 2 weeks, but this can be altered based on a number of factors.
  • The Longer the scale the less time is required between measurements (the person is less likely to remember all of their answers).
  • Duration is also determined by how quickly the attribute being tested can change.

References

1.
Koo TK, Li MY. A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research. Journal of Chiropractic Medicine. 2016;15(2):155-163. doi:10.1016/j.jcm.2016.02.012
2.
Streiner DL. Statistics Commentary Series: Commentary #15-Reliability. Journal of Clinical Psychopharmacology. 2016;36(4):305-307. doi:10.1097/JCP.0000000000000517

Citation

For attribution, please cite this work as: