reliability

When sociologists enquire as to the reliability of data, or of a measurement procedure, they are questioning whether the same results would be produced if the research procedure were to be repeated. Reliability embraces two principal forms of repetition: temporal reliability (the same result is obtained when the measurement is repeated at a later time); and comparative reliability (the same result is obtained when two different forms of a test are used, the same test is applied by different researchers, or the same test is applied to two different samples taken from the same population). Reliability raises many technical problems for the sociologist. For example, having once interviewed someone, a repeat interview may be contaminated by the earlier experience.

Reliability is usually contrasted with validity -whether or not a measurement procedure actually measures what the researcher supposes it does. However the two are not perfectly independent. One may have a highly reliable measure which is not valid: for example, we might measure IQ by standing subjects on a weighing machine and reading off the numbers, an extremely reliable procedure in both senses; but body-weight is hardly a valid indicator of IQ. A highly unreliable measure, on the other hand, cannot be valid. See also variable.