Summary
When measuring any variable, from a physical trait to a more ill defined behavioral characteristic, two things must be assessed, reliability and validity. A measurement must have both properties, just one is not sufficient.
When assessing reliability and validity it is the job of the user of the measurement to look for sources of error, both random and non-random, which might be threats to reliability and validity.
References
1 Carmines EG, Zeller RA. Reliability and Validity Assessment, 1983, Sage University Paper 07-017, Sage Publications: Beverly Hills, CA.
2 American Psychological Association, American Educational Research Association, National Council for Measurement in Education, Standards for Educational and Psychological Testing. 2004, AERA, Washington DC.
If you want to know more:
