Mining the Optimal Clustering of People's Characteristics of Health Care Choices

抄録

In Asian countries, it has been a multi-choice environment of health care for a long time. However, especially in Taiwan, people's multiple health care seeking behavior has resulted in much heavier financial burden of National Health Insurance (NHI) in recent years. In this study, we investigated the socioeconomic and demo- graphic factors underlying people's intention of different health care choices by using data of the first wave Taiwan National Health Interview Survey (NHIS) conducted in 2001. We proposed a new methodology that incorporating k-means cluster analysis with v-fold cross-validation into Multiple Correspondence Analysis (MCA), which can help us to find the optimal number of attribute clusters. By using this methodology, we not only can avoid the disadvantages of ambiguities of traditional hierarchical cluster analysis (HCA) when the number of subjects increases, but also can provide more solid and evidence-based analysis for health policy making.