Subscribe to DSC Newsletter

Theophano Mitsa
  • Melrose, MA
  • United States
Share on Facebook

Theophano Mitsa's Friends

  • Remi Mollicone
  • hsingh
  • Sarah Danish
  • Ray Burton
  • Vincent Granville

Theophano Mitsa's Page

Profile Information

Self employed
Job Function:
Predictive Modeling, Data Mining, Statistical Consulting, Medical Statistics, Artificial Intelligence
Short Bio:
Dr. Mitsa holds a Ph.D. degree in Electrical Engineering from the University of Rochester and is the author of 47 publications, 10 U.S. patents and the book (CRC Press, 2010) “Temporal Data Mining”. She has diverse academic and industrial experience, having served as a faculty member at the Universities of Iowa and Massachusetts and a Senior Software Engineer at GE HealthCare and Abiomed. Dr. Mitsa has received awards from the National Science Foundation, the Whitaker Foundation, HP, and the Fulbright program. Her most recent patent (8/2012), is on a decision-support system for adaptive hybrid reasoning. She is currently an Independent Data Mining/Machine Learning Consultant.
LinkedIn Profile:

Website for my blog and my book

Comment Wall

You need to be a member of AnalyticBridge to add comments!

Join AnalyticBridge

  • No comments yet!

Theophano Mitsa's Blog

Cross-validation in R: a do-it-yourself and a black box approach

Posted on May 22, 2013 at 8:06am 2 Comments

In my previous post, we saw that R-squared  can lead to a misleading interpretation of the quality of our regression fit, in terms of prediction power. One thing that R-squared offers no protection against is overfitting. On the other hand, cross validation, by allowing us to have cases in our testing set that are different from the cases in our training set,  inherently offers protection against overfittting.

1.Do-it-yourself leave-one-out cross validation in R.

In this type…


Use PRESS, not R squared to judge predictive power of regression

Posted on May 12, 2013 at 9:00am 4 Comments

R squared, also known as coefficient of determination, is a popular measure of quality of fit in regression. However, it does not offer any significant insights into how well our regression model can predict future values. Instead, the PRESS statistic (the predicted residual sum of squares) can be used as a measure of predictive power. The PRESS statistic can be computed in the leave-one-out cross validation…


On Data Science Central

© 2021   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service