Moving from Descriptive to Causal Analytics: Case Study of the Health Indicators Warehouse

Conference · Sun Jan 01 00:00:00 EST 2012

OSTI ID:1056946

Schryver, Jack C. ^[1]; Shankar, Mallikarjun ^[1]; Xu, Songhua ^[1]

---

1. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

The KDD community has described a multitude of methods for knowledge discovery on large datasets. We consider some of these methods and integrate them into an analyst s workflow that proceeds from the data-centric descriptive level to the model-centric causal level. Examples of the workflow are shown for the Health Indicators Warehouse, which is a public database for community health information that is a potent resource for conducting data science on a medium scale. We demonstrate the potential of HIW as a source of serious visual analytics efforts by showing correlation matrix visualizations, multivariate outlier analysis, multiple linear regression of Medicare costs, and scatterplot matrices for a broad set of health indicators. We conclude by sketching the first steps toward a causal dependence hypothesis.

• Research Organization: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1056946
• Resource Relation: Conference: ACM SIGKDD Workshop on Health Informatics 2012 (HI-KDD 2012) , Beijing, China, 20120812, 20120812,
• Country of Publication: United States
• Language: English