Regression Estimation Diagnostics Measures for High-Dimensional Regression

• Activity Number: 547
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Yanjia Yu* and Yuhong Yang
• Companies: University of Minnesota, Twin Cities and University of Minnesota, Twin Cities
• Keywords: Model Combining ; Big Data ; High Dimensional Data ; Statistical Application ; Machine Learning ; Model Selection

Abstract

We now live in a big data world. Big data is of practical use. We can build up statistical models to make predictions with the data we got. However, which statistical model to choose? Is one model better than the other with respect to the reliability of predictive performance? Or will model averaging provide us a better result? If we know when and how to choose a specific model, it will help us get a more reliable and accurate prediction and also make the predictive modeling more efficient.

In this paper, we proposed regression estimation diagnostics measures to help provide some sense on the reliability of different predictive models considered. And hopefully, it can provide some thoughts on the previous questions.