區別效度/發散效度

Discriminant validity is “the degree to which concepts that should not be related theoretically are not interrelated in reality.”
Reference: Campbell DT, Fiske DW. (1959). Convergent and discriminant validation by the multitrait- multimethod matrix. Psychological Bulletin, 56, 81-105.

Campbell & Fiske (1959) 在其文章給予discriminant validity上述的解釋，Nunnally& Bernstein (1994)在其書中引用Campbell & Fiske (1959) 關於discriminant validity 的定義並稱之為divergent validity，由此可知兩詞可互用。

Divergent validity : "In order to justify novel measures of attributes, a measure should have divergent validity in the sense of meauring something different from existing methods. Measures of different attributes should therefore not correlate to an extremely high degree." (pp. 92)
Reference : Nunnally JC, Bernstein IH. Psychometric theory. McGraw-Hill, INC. ;1994.

區辨效度: 指評估工具本身的分數，應該和測量不同構念或特質的評估工具之分數，有低相關（甚至無關）。

判斷標準:可使用相關係數來驗證:相關係數<0.3，表示兩評估工具評估到的特質部相關。

研究設計: 個案同時接受欲驗證的評估工具及不同構念或特質的評估工具之評估

Ng TP, Niti M, Chiam PC, Kua EH. Physical and cognitive domains of the instrumental activities of daily living: Validation in a multiethnic population of Asian older adults. J Gerontol A Biol Sci Med Sci. 2006; 61: 726-735.

 

區辨效度亦稱發散效度，為建構效度之一種，以巴氏量表為例，施測者使用巴氏量表能正確有效地評估到中風個案的日常生活活動功能，而非評估到個案的認知或憂鬱程度。