You\u2019ve learned how a personality test like BLIRT can be designed and refined. The next step is just as important: showing that the test is valid<\/b><\/span>.<\/p>\r\n A test is valid<\/b><\/span> if it measures what it is supposed to measure. In other words, validity evidence answers the question:<\/p>\r\n Validity<\/b><\/span> is the degree to which evidence supports the interpretation and use of test scores for a particular purpose.<\/p>\r\n Psychologists often build validity evidence in several ways, including:<\/p>\r\n Convergent validity:<\/b><\/span> BLIRT scores relate to similar<\/b><\/span> traits and measures<\/p>\r\n<\/li>\r\n\t Discriminant validity:<\/b><\/span> BLIRT scores do not<\/b><\/span> relate strongly to unrelated<\/b><\/span> traits<\/p>\r\n<\/li>\r\n\t Criterion validity:<\/b><\/span> BLIRT scores relate to a meaningful real-world outcome<\/b><\/b><\/span><\/p>\r\n<\/li>\r\n\t Predictive validity:<\/b> BLIRT scores help <\/span>predict future behavior<\/b> in relevant situations<\/span><\/p>\r\n<\/li>\r\n<\/ul>\r\n<\/section>\r\n One way to test validity is to compare your new scale with other measures that already have strong evidence behind them.<\/p>\r\n For convergent validity<\/b><\/span>, researchers choose traits that are related to<\/b><\/span> blirtatiousness, but not identical. For example, blirtatiousness involves fast, expressive responding\u2014so it makes sense that it might relate to traits like:<\/p>\r\n If BLIRT scores were not<\/i> related to any of these, that would raise concerns that BLIRT is not measuring what it claims to measure.<\/p>\r\n To test this, Swann\u2019s team gave the BLIRT scale and several related measures (including a measure of assertiveness<\/b><\/span>[footnote]The Rathus Assertiveness Schedule[\/footnote]) to 1,397 college students<\/b><\/span>.<\/p>\r\n Convergent validity asks, \u201cDoes BLIRT relate to what it should<\/i> relate to?\u201d Discriminant validity<\/b> asks the flip side:<\/span><\/p>\r\n Researchers compare BLIRT scores to traits or outcomes that should have little or no connection<\/b><\/span> to blirtatiousness.<\/p>\r\n For example, BLIRT measures conversational style\u2014how quickly and emotionally someone responds\u2014not academic skill. So knowing someone\u2019s BLIRT score should not tell you much about their GPA.<\/p>\r\n Swann\u2019s team compared BLIRT scores to self-reported GPA<\/b><\/span> and other traits expected to be less related to blirtatiousness.[footnote]Other traits included agreeableness, conscientiousness, and affect intensity (how strongly people experience emotions).[\/footnote]<\/p>\r\n<\/div>\r\n Overall, BLIRT performed the way a valid scale should: it was related to similar traits (good convergent validity) and weakly related\u2014or unrelated\u2014to traits that didn\u2019t conceptually fit (good discriminant validity).<\/p>\r\n Who do you predict would score higher on blirtatiousness: car salespeople<\/span> or librarians<\/span>?<\/p>\r\n Swann\u2019s team administered the BLIRT to 30 employees<\/span> at car dealerships and libraries in central Texas (ages 20\u201366; average age 34.3). Most people expect salespeople to be more blirtatious because that job often rewards fast, expressive talk, while library work may reward reflection and restraint.<\/p>\r\nWhen someone scores high (or low) on BLIRT, does that score actually mean they are more (or less) blirtatious in real life?<\/blockquote>\r\n
validity<\/h3>\r\n
\r\n\t
Convergent Validity<\/h3>\r\n
\r\n\t
Discriminant Validity<\/b><\/h3>\r\n
\u201cDoes BLIRT not<\/i> relate to what it shouldn\u2019t relate to?\u201d<\/blockquote>\r\n
Librarians or salespeople?<\/b><\/h3>\r\n
Prediction check<\/b><\/h3>\r\n\r\nUsing the bar graph below, adjust the bars based on your prediction about who will be more blirtatious. Then click the link below to see if your prediction is correct.