Libertie Mantilla
Department of Statistics
Western Michigan University
Multivariate mixed design data is a mixture of paired and independent samples. Data of this type can arise in a study with a matched-pair design in which due to some circumstances, part of the sample may have responses only on one element of a pair. Hence, there are complete data obtained from a matched pair (n0) and partial data from only the first element (n1) or second (n2) element of a configured pair. The objective of this paper is to propose a procedure for estimation and hypothesis testing that make use of all the available data. The proposed methodology will be illustrated with some examples. A simulation study to assess the power, size, and efficiency of the proposed method will be presented.
All statistics students are expected to attend.