To Fit or Not to Fit Data to a Model
What if Shakespeare was a data scientist? Today's big data necessitates - Let the data define the model.
By Bruce Ratner, GenIQ.net
To fit or not to fit data to a model - that is the question:
Whether 'tis nobler in the mind to suffer
The slings and arrows of outrageously using
The statistical regression paradigm of
Fitting data to a pre-specified(!) model, conceived and tested
Within the small-data setting of the day, 206 years ago,
Or to take arms against a sea of troubles
And, by opposing, move aside fitting data to a model.
Today's big data necessitates - Let the data define the model.
Fitting big data to a pre-specified small-framed model
Produces a skewed model with
Doubt interpretability and questionable results.
When we have shuffled off the expected coil,
There's the respect of the GenIQ Model,
A machine-learning alternative regression model
To the statistical regression model.
GenIQ is an assumption-free, free-form model that
Maximizes the cum lift statistic, equally, the decile table.
This was originally published at http://www.geniq.net/res/Shakespearian-Modelogue.html.
Bruce Ratner, Ph.D., The Significant Statistician™, is President and Founder of DM STAT-1 Consulting, and the author of the best-selling book Statistical and Machine-Learning Data Mining: Techniques for Better Predictive Modeling and Analysis of Big Data.