Reliability and Validity

Reliability and Validity

Reliability implies consistency or stability, but it may also imply dependability. There are several different types of reliability. The first one is alternate-form reliability it is the degree of relatedness of different forms of the same test. This type is the overall degree of relatedness of all items in a test or all rates in a judgment study (also called reliability of components) (Rosnow, Rosental, 2008). The next type of reliability is item-to-item reliability which is any single item on average and analogous to judge-to-judge reliability, which is reliable of any single judge on average (Rosnow, Rosental, 2008). The last type is test-retest reliability and this is the degree of temporal stability of a measuring instrument or test or the characteristics it is designed to evaluate, from one administration to another which is also called retest reliability (Rosnow, Rosental, 2008).

Validity shows how well the measure or design does what its purpose it to do. There are many types of validity. Construct validity is the degree which the conceptualization of what is being measured or experimentally manipulated is what is claimed such as the constructs that are measured by psychological tests or that serve as a link between independent and dependent variables (Rosnow, Rosental, 2008). Content validity is an adequate sampling of relevant material or content that a test purports to measure. Convergent and discriminant validity is established for a construct based on the convergence of related test or behavior and the distinctiveness of unrelated tests or behavior. Criterion validity is the degree to which a test or questionnaire is correlated with outcome criteria in the present or the future. External validity is the generalization of an inferred causal relationship such as people, setting, manipulation, treatments, and research outcomes. Face validity is the degree to which a test or other instrument "looks as if" it is measuring something relevant. Internal validity is the soundness of statements about whether one variable is the cause of a particular outcome. The last type of validity is statistical-conclusion validity is the accuracy of drawing certain statistical conclusions, like an estimation of the degree of statistical significance of a particular statistical test (Rosnow, Rosental, 2008).