Research Seminar
Clusterwise HICLAS: A generic modeling strategy to trace similarities and differences in multi-block binary dataTom WilderjansKU Leuven | |
| Abstract: | When studying multi-block binary data (e.g., successive multivariate binary observations of caretakers reactions for different clients), a major challenge pertains to uncovering the differences and similarities between the structural mechanisms that underlie the different blocks (e.g., inter-client differences/similarities in reactions of caretakers to client behaviors). To tackle this challenge for the case of a single data block (e.g., one client), one may rely on HICLAS (De Boeck & Rosenberg, 1988). In case of multiple binary data blocks, one may perform HICLAS to each data block separately. However, such an analysis strategy obscures the similarities and, in case of many data blocks, also the differences between the blocks. To resolve this, we propose the new Clusterwise HICLAS generic modeling strategy. In this strategy, the different data blocks are assumed to form a set of mutually exclusive clusters. For each cluster, different underlying mechanisms are derived. As such, blocks belonging to the same cluster have the same underlying mechanisms, whereas blocks of different clusters are modeled with different mechanisms. Further, the performance of Clusterwise HICLAS is evaluated by means of an extensive simulation study, and by applying the strategy to empirical multi-block binary data. |
| Date: | Tue Nov 15, 12:00 pm - 1:00 pm |
| Place: | room 01.07 (Department of Psychology, Tiensestraat 102, 3000 Leuven) |