A PROBLEM WITH DISCRETIZING VALE–MAURELLI IN SIMULATION STUDIES

Foldnes, Njål; Grønneberg, Steffen
Journal article, Peer reviewed
Accepted version
Thumbnail
View/Open
URI
http://hdl.handle.net/11250/2599455
Date
2019
Metadata
Show full item record
Collections
Original version
Psychometrika.2019, 84 (2), 554–561.   https://doi.org/10.1007/s11336-019-09663-8
Abstract
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.
Publisher
Springer
Journal
Psychometrika
Copyright
Copyright policy of Springer, the publisher of this journal: "Authors may self-archive the author’s accepted manuscript of their articles on their own websites. Authors may also deposit this version of the article in any repository, provided it is only made publicly available 12 months after official publication or later. He/ she may not use the publisher's version (the final article), which is posted on SpringerLink and other Springer websites, for the purpose of self-archiving or deposit…”