We begin our tour of psychometric modeling paradigms with classical test theory (CTT). Textbook treatments and overviews of CTT from a conventional perspective can be found in Crocker and Algina (1986), Lewis (2007), Lord and Novick (1968), and McDonald (1999). The CTT model has been conceived of in several distinct ways, differing in terms of whether an author develops the model from single or multiple observables, and from one of several different distributional notions of error (cf. Bollen, 1989; Haertel, 2006; Lewis, 2007; Lord & Novick, 1968; McDonald, 1999). What follows is a cursory treatment of the model focusing on consensus notions. Readers are referred to the above cited works for considerably more details ...
Get Bayesian Psychometric Modeling now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
