MULTILEVEL MODELING OF EDUCATIONAL DATA WITH CROSS-CLASSIFICATION ANDMISSING IDENTIFICATION FOR UNITS

This paper presents a method for handling educational data in which st udents belong to more than one unit at a given level, but there is mis sing information on the identification of the units to which students belong. For example, a student might be classified as belonging sequen tially to a particular combination of primary and secondary school, bu t for some students the identify of either the primary or the secondar y school may be unknown. Similar situations arise in longitudinal stud ies in which students change school or class from one year to the next . The method involves setting up a cross-classified model, bur replaci ng (0, 1) values for unit membership with weights reflecting probabili ties of unit membership in cases where membership information is rando mly missing. The method is illustrated with reference to longitudinal data on students' progress in English.