Premium
A method for obtaining randomized block designs in preclinical studies with multiple quantitative blocking variables
Author(s) -
Iturria Stephen J.
Publication year - 2011
Publication title -
pharmaceutical statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.421
H-Index - 38
eISSN - 1539-1612
pISSN - 1539-1604
DOI - 10.1002/pst.445
Subject(s) - blocking (statistics) , covariate , context (archaeology) , block (permutation group theory) , computer science , randomization , multivariate statistics , hierarchical clustering , cluster analysis , mathematics , statistics , mathematical optimization , algorithm , data mining , randomized controlled trial , medicine , paleontology , geometry , surgery , biology
Abstract A method is proposed for block randomization of treatments to experimental units that can accommodate both multiple quantitative blocking variables and unbalanced designs. Hierarchical clustering in conjunction with leaf‐order optimization is used to block experimental units in multivariate space. The method is illustrated in the context of a diabetic mouse assay. A simulation study is presented to explore the utility of the proposed randomization method relative to that of a completely randomized approach, both in the presence and absence of covariate adjustment. An example R function is provided to illustrate the implementation of the method. Copyright © 2010 John Wiley & Sons, Ltd.