This paper describes procedures for estimating single-administration classification consistency and accuracy indices using item response theory (IRT). This IRT approach is applied to real test data comprised of mixtures of dichotomous and polytomous items. Several different IRT model mixtures are considered. Comparisons are made between the IRT approach and two non-IRT procedures.

OBJECTIVE Because cystic fibrosis can be difficult to diagnose and treat early, newborn screening programs have rapidly developed nationwide but methods vary widely. We therefore investigated the costs and consequences or specific outcomes of the 2 most commonly used methods. METHODS With available data on screening and follow-up, we used a simulation approach with decision trees to compare i...

the classical test theory (ctt) and item response theory (irt) are widely used in construction and analysis of exams and questionnaires. because of the various shortcomings of ctt, irt has been designed. even though irt has overcome most of the limitations of ctt and has made computer adaptive testing possible, it is still important to point out that not enough reasons exist to totally discard ...

AIMS To investigate the immunoreactive trypsinogen (IRT) values above the usual 99th centile laboratory cut-off and determine the value of offering further testing to those infants with a markedly elevated IRT but no cystic fibrosis transmembrane regulator (CFTR) gene mutation identified by the screening programme. METHODS All babies born in Victoria, Australia, between 1991 and 2003, were sc...

OBJECTIVE To compare three cystic fibrosis (CF) newborn screening strategies used in Victoria since 1989. DESIGN, SETTING AND PARTICIPANTS Retrospective review of newborn screening and clinical records for people with CF born in Victoria between 1989 and 2008 to compare screening strategies: repeat immunoreactive trypsinogen (IRT) testing (IRT/IRT, 1989-1990), IRT and p.F508del mutation analy...