Defending the Quality of Links Between Scores from Different Tests and Exams

摘要

Paul Newton (2010), with his characteristic concern about theory, has set out two different ways of thinking about the basis upon which equivalences of one sort or another are established between test score scales. His reason for doing this is a desire to establish "the defensibility of linkages lower on the continuum than concordance." His ultimate aim, although he is too modest to claim he has achieved it, appears to be to develop a generally accepted theoretical paradigm (in the Kuhnian sense) to which practitioners of linking can appeal in order to defend what they have done. As I understand it, Paul's principal complaint about what he calls the continuum and deficit rhetorics is encapsulated in his question: "But what criteria exist for judging the defensibility of linkages lower on the continuum than concordance, such as vertical scaling, battery scaling and anchor scaling?"