幾個有關Rasch測量模式的爭議

Abstract

現今的測量理論裡，常把Rasch(音譯為羅許)模式和Birnbaum的二參數模 式和三參數模式相提並論。不少的學者都規Rasch模式只是二參數模式的特例， 因而特別推崇二或三參數模式。本文分別從模式裡的量尺，參數的意義，選擇題 的猜測行為，向度，模式的發展性等層面，說明只有Rasch模式才是測量的模式， 而二參數模式和三參數模式只是統計模式，沒有測量的意義。如果測驗資料符合 Rasch模式的話，那麼這個變項已被量化了。一旦測驗資料不吻合Rasch模式，是 否仍該堅持Rasch模式呢?這個Rasch爭辯還在持續進行著。事實上，這個爭議可以 透過對客觀測量的理解而加以澄清。就建構定義的發展階段上，如果直接由理論 推導即可獲致試題特性，毋需經過實證資料的檢驗，那麼就達到和自然科學界測 量一樣的普遍性客觀。

In modern measurement theory, the Rasch model and Birnbaum`s two-or three- parameter models among others together form so called itemresponse theory. Many researchers treat the Rasch model as a specialcase of the two-parameter model, and not thing more. Therefore, the two- and three- parameter models are highly recommended. In this paper, Icompare the Rasch model with the two- and three- parameter models onthe following aspects: scales in the models, meaning of the parameters,dimensionality, guessing in multiple-choice items, and model development . Iconcludes that only the Rasch model is a genuine measurement model, andthe two- and the three- parameter models are only statistical modelswithout measurement per se. Consequently, the Rasch model is anecessary condition for measurement . If test data do not fit the Raschmodel, should we still insist on the Rasch model and modify the test dataor switch to multiparameter models? This Rasch debate is still lasting. Inthis paper, I show how the debate can be resolved through recognition ofobjective measurement. Furthermore, if item difficulties can be inferreddirectly from test construct theory instead of from real data analyses,general objectivity is achieved, as in the natural sciences.