Research Tips
Validity
“Validity”, like “reliability”, has a more specific meaning for research purposes than it does in everyday language. When researchers talk about validity, what they mean is “the extent to which any measuring instrument measures what it is intended to measure”.1
Ensuring a measurement instrument, such as a questionnaire, is valid is important because if it’s not valid, then the results generated may be misleading. For example, suppose a company is interested in finding out whether a new ad campaign will result in increased sales, and to investigate this they have people view the ads and complete a questionnaire that asks whether the ads were interesting and enjoyable. Such a questionnaire would not provide a valid measurement of what the company is interested in — increased sales. It would only provide a valid measurement of attitudes toward the ad campaign, which might or might not be correlated with sales.
It’s important to note that a measurement instrument must be reliable to be valid, but it may be reliable and not valid.
1 Carmines, Edward G. and Richard A. Zeller (1991), Reliability and Validity Assessment, page 17.