A PROBLEM WITH DISCRETIZING VALE–MAURELLI IN SIMULATION STUDIES
Journal article, Peer reviewed
MetadataShow full item record
Original versionPsychometrika.2019, 84 (2), 554–561. https://doi.org/10.1007/s11336-019-09663-8
Previous influential simulation studies investigate the effect of underlying non-normality in ordinal data using the Vale–Maurelli (VM) simulation method. We show that discretized data stemming from the VM method with a prescribed target covariance matrix are usually numerically equal to data stemming from discretizing a multivariate normal vector. This normal vector has, however, a different covariance matrix than the target. It follows that these simulation studies have in fact studied data stemming from normal data with a possibly misspecified covariance structure. This observation affects the interpretation of previous simulation studies.