Experiences from a Socio-economic Application of Induction Trees

This paper presents a full scaled application of induction trees for non-classificatory purposes. The grown trees are used for highlighting regional differences in the women's labor participation, by using data from the Swiss Population Census. Hence, the focus is on their descriptive rather than predictive power. A first tree provides evidence for three separate analyses for non-mothers, married or widowed mothers, and divorced or single mothers. For each group, trees grown by language regions exhibit fundamental cultural differences supporting the hypothesis of cultural models in female participation. From the methodological standpoint, the main difficulties with such a non-classificatory use of trees have to do with their validation, since the classical classification error rate does not make sense in this setting. We comment on this aspect and consider alternatives that are both consistent with our non-classificatory usage and easy to compute.

• Type: Conference
• Year: 2006
• Where: DIS
• Authors: Fabio B. Losa, Pau Origoni, Gilbert Ritschard
• Keywords: DIS 2006, Grown Trees, Induction Trees, Theoretical Computer Science, Women's Labor Participation