Definition
Validity is a term applied to measuring instruments reflecting the extent to which differences in scores on the marketing measurement reflect true differences among individuals, groups, or situations in the characteristic it seeks to measure – or true differences in the same individual, group, or situation from one occasion to another – rather than constant or random errors.
Here are several approaches to validating a measure:
Construct validation – determining what construct, concept, or trait the instrument is in fact measuring.
Content validity – determining the adequacy with which a characteristic is captured by the measure; i.e., the degree to which a test or metric appears effective in terms of its stated aims.
Convergent validity – confirming the existence of a construct determined by the correlations exhibited by independent measures.
Discriminant validity – imposing criterion on a measure of a construct requiring that it not correlate too highly with measures from which it is supposed to differ.
External validity – the extent (to what populations and settings) to which the observed experimental effect can be generalized.
Face validity (sometimes called logical validity or surface validity) – the degree to which a test subjectively appears to measure the variable or construct that it’s supposed to measure. It is merely a subjective, superficial assessment of whether the measurement procedure you use in a study appears to be a valid measure of a given variable or construct.
Internal validity – obtaining evidence demonstrating that the variation in the criterion variable was the result of exposure to the treatment or experimental variable.
Predictive validity (sometimes called pragmatic validity or criterion-related validity)– evaluating the usefulness of the measuring instrument as a predictor of some other characteristic or behavior of the individual.
References
- American Marketing Association, AMA Dictionary.