R squared Does Not Measure Predictive Capacity or Statistical Adequacy

R squared Does Not Measure Predictive Capacity or Statistical Adequacy

The fact that R-squared shouldn't be used for deciding if you have an adequate model is counter-intuitive and is rarely explained clearly. This demonstration overviews how R-squared goodness-of-fit works in regression analysis and correlations, while showing why it is not a measure of statistical adequacy, so should not suggest anything…

16 mentions: @kdnuggets@iamalexbirkett@rzembo@DrMikeWatts@LebenTech@dataclaudius@georgizgeorgiev
Date: 2020/08/01 18:53

Referring Tweets

@georgizgeorgiev Venturing into observational analyses with an article for KDnuggets on R squared, an often misunderstood statistic. I hope you appreciate it. t.co/SrAUYXdHt0 #statistics #regression #regressionanalysis #correlation
@kdnuggets A demonstration of how R-squared goodness-of-fit really works -- and how it should not be used as a way to pick the best predictive model. t.co/Nf1BbopLr1 @georgizgeorgiev t.co/j3VIGUoT8U

Related Entries

Read more Top KDnuggets tweets, May 13-19: Linear algebra and optimization and machine learning: A textbook
0 users, 11 mentions 2020/05/24 12:58
Read more Top KDnuggets tweets, May 20-26: The Best NLP with Deep Learning Course is Free
0 users, 9 mentions 2020/05/27 21:51
Read more The Unreasonable Progress of Deep Neural Networks in Natural Language Processing (NLP)
0 users, 24 mentions 2020/07/02 21:53
Read more Understanding How Neural Networks Think
0 users, 21 mentions 2020/07/16 14:21
Read more Top Stories, Jul 13-19: The Bitter Lesson of Machine Learning
0 users, 16 mentions 2020/07/20 17:07