Major Types of Validity:

Different aspects or facets of  validity  questions are explained by  the type of validity, and number of  indirect and logical methods have evolved to  assess validity. 

a)  Content  Validity: This is concerned with the sampling adequacy of the content area being measured. It  refers  to  the  fact  that the items included in -the tool represent a reasonable sampling of all possible  itemshehaviours that make the domain being measured. The content area to be  tested must first be  studied to make certain  that  all major aspects or subcategories are represented in  correct proportions. Experts  in  the content area are often called upon  to analyse the items to see  if  they adequately represent not only the content universe (or domain) but  also  in  cohect proportions. They also point  out errors and ambiguities in items and make recommendations for changes. Content validity assessment also involves a more elaborate procedure by which  items are developed, given  to  experts for judgment and determination of percentage of items for each category. Percentage of agreement between the judges  is considered as  the basis for inclusion or rejection of items. After  item  analysis, content validity needs to be  assessed again to determine if the correct proportion of items for each subcategory has  been maintained. If  the proportion has not been maintained, exchange of items and sometimes addition of items are made until the content is sampled appropriately while retaining an  acceptable level of reliability. 

b)  Criterion-related Validity: Seeks to establish that the measure correlates to another criterion rather than  to ascertain how well the tool measure the particular phenomenon. For  example, the instrument measuring anxiety state is  said  to  be  valid if  the anxiety scores correlate with some criterion, such as, persons who  are known  to be  anxious  (e.g.  student prior to a difficult examination) would  be expected to have high scores on the anxiety scale. That  is, groups known to possess or not  to possess the characteristics being measured would be  the criterion. Sometimes distinctions are made between two types of criterion validity, predictive and concurrent. Predictive validity  refers to  the adequacy of  an instrument  in predicting performance or behaviour of  individuals on some fbture criteria, e.g. how well does the admission test predict the future performance of  the student. This can be got  by  correlating admission  test scores of  first year nursing students with  subsequent achievement in nursing  in  second, third and kourth  year. Here, the predictive validity of admission test for nursing  is being evaluated. 

c)  Concurrent Validity, on  the other hand, involves concurrent (i.e. simultaneous) measurement of  the scale being validated. The difference between predictive and concurrent validity, then, is the difference in timing of obtaining measurements on a criterion. One of the hardest aspects of criterion related validity  is  selection and measurement of  criterion. It must  be  relevant, possess  reliability and validity and be free  from bias.