"Two Big Ideas for 'Big Data' Analytics"
Milo Schield, Augsburg College
Abstract
Description: Confounding and coincidence are two statistical influences that dominate when dealing with "big data." These ideas are being taught in Augsburg's "Statistical Literacy for Managers" course using Excel.
Participants will access PowerPoint slides that demonstrate the influence of confounding on OLS regression, on logistic regression and on other multivariate models using Excel.
- www.statlit.org/pdf/Model-Regress-Linear-3Factor-QBB-Excel2013-6up.pdf
- www.statlit.org/pdf/Model-Regress-Logistic-3Factor-BQB-Excel2013-6up.pdf
Participants will demonstrate how coincidences are expected in "Big Data" using Excel.
Engagement: Participants will be encouraged to (1) form generalizations on the influence of confounding and coincidence as the number of data records increases, (2) discuss the importance of teaching these ideas in introductory statistics, and (3) discuss the ease or difficulty in teaching these ideas using Excel.
Take-away: Participants should have a better idea of what might be taught when dealing with big data in introductory statistics.
Materials
Recording
(Tip: click the fullscreen control)
Having trouble viewing? Try: Download (.mp4)
(Tip: right-click and choose "Save As...")
Comments
No comments.