Blog8_Statistics Denial H, Myth 4, Distribution FINAL

Blog 8: Statistics Denial Myth #4, Rebranding Predictive Modeling

Randy Bartlett

Randy Bartlett, Ph.D. CAP® PSTAT® is a statistician/statistical data scientist with 20+ years of practice experience analyzing and reviewing data analysis; and leading business analytics teams.He designed 'A Practitioner’s Guide to Business Analytics' to be the foremost reference on how corporations can better implement business analytics and in this era of Big Data.

Blog 8: Statistics Denial Myth #4, Rebranding Predictive Modeling

This blog discusses the ambition of rebranding predictive modeling as predictive analytics; and why this will enlarge the coming flood of statistical malfeasance.  The prediction problem involves uncertainty and statistics provides us with the tools, language, and thinking for addressing numbers with uncertainty.  We have provided a problem-based clarification of statistics in Analytics Magazine.  This should help people better identify statistics problems.

Rebranding & Mischaracterizing Predictive Modeling:

The rebranding of predictive modeling as predictive analytics is on its surface no more harmful than selling 'pre-owned cars' instead of 'used cars.'  The harm comes when rebranding mischaracterizes statistics and circumvents best practice.  As mentioned before, the concern with rebranding is that the next step is to strip away everything not understood by those merely following recipes.

Here is a quote that captures the problematic mischaracterization, 'PREDICTIVE ANALYTICS does NOT require an understanding of “STATISTICS / TRADITIONAL p-value STATISTICS” …. Period !!!!!'  This objection spreads rudimentary misunderstandings about statistics.  Here is another quote, 'It [predictive modeling] is not a [sub]field of statistics.'

The only useful function for a statistician is to make predictions, and thus provide a basis for action.W. Edwards Deming

First, prediction has always been a subfield of statistics.  We need to look no further than the fact that prediction involves uncertainty.  Let us recap the four common objectives for statistics models: coefficient estimation, prediction (there it is!), grouping, and ranking.  Those new to the subject want to rename and reclassify everything as part of their rediscovery.

Second, note the qualification from the first quote, 'statistics/traditional p-value statistics.'  This is like claiming that division does not require an understanding of 'mathematics/traditional addition.'

Read Also:
Evaluating your need for a data warehouse platform

Here is a third quote, "PA [Predictive Analytics] and DS [Data Science] both contrast with statistics in their emphasis on prediction over causality and their general use of observational in contrast to experimental methods."  PA and DS are rebrandings of predictive modeling and statistics, respectively with no change in content.  All of the assumptions, thinking, and tools for dealing with uncertainty are statistical.

First, that 'predictive analytics emphasizes prediction over statistics' is just babble.  Similarly, we could claim that predictive modeling emphasizes prediction over statistics and sampling emphasizes sampling over statistics too.  We could claim that 'Division Scientists' perform more division than Mathematicians.  This does not express a new value proposition for predictive analytics.  In general, this boils down to a comparison between topical areas like commercial statistics and clinical statistics.  This distinction is lost when an applied statistician moves from clinical to commercial.

Second, the same confused type of claim is repeated with the idea that predictive analytics is more about observational data than statistics.  Again, this is like claiming that predictive modeling is more about observational data than statistics.  There is nothing new in this rebranding that is not in predictive modeling—a subfield of statistics.

Third, statistics places a heavy emphasis on analyzing observational data and it does this in a number of subfields: predictive modeling, DoS (Design of Samples), QC/PC (Quality Control/Process Control), Times Series, EDA (Exploratory Data Analysis), et al.  Hence, statistics is more about observational data than predictive analytics.  Observational data contains uncertainty.

Close:

Predictive analytics is a rebranding of predictive modeling for promotional purposes.  We can be certain that prediction is a statistics problem because it involves numbers with uncertainty.  Claiming prediction does not require an understanding of statistics is like claiming that division does not require an understanding of mathematics.

Rebranding can have some benefits if performed thoughtfully.  However, we think that there is nothing thoughtful or measured in denying the value proposition of statistics.  The downside of rebranding is that important parts can be omitted just because they are not understood by recipe followers.  We have noticed that self-professed experts in predictive analytics seldom discuss prediction intervals!?  Corrupting prediction modeling will facilitate a flood of statistical malfeasance.

Read Also:
How to Make Better Predictions When You Don’t Have Enough Data

We sure could use Deming, right now.  Many of us, who consume or produce data analysis, hang out in the new LinkedIn group: About Data Analysis.  Come see us.



Randy Bartlett

Randy Bartlett, Ph.D. CAP® PSTAT® is a statistician/statistical data scientist with 20+ years of practice experience analyzing and reviewing data analysis; and leading business analytics teams.He designed 'A Practitioner’s Guide to Business Analytics' to be the foremost reference on how corporations can better implement business analytics and in this era of Big Data.

Blog 8: Statistics Denial Myth #4, Rebranding Predictive Modeling



Chief Analytics Officer Europe

off with code

Read Also:
Big Data: Now an Integral Part of Talent Recruiting

Randy Bartlett

Randy Bartlett, Ph.D. CAP® PSTAT® is a statistician/statistical data scientist with 20+ years of practice experience analyzing and reviewing data analysis; and leading business analytics teams.He designed 'A Practitioner’s Guide to Business Analytics' to be the foremost reference on how corporations can better implement business analytics and in this era of Big Data.

Blog 8: Statistics Denial Myth #4, Rebranding Predictive Modeling



Chief Analytics Officer Spring 2017

off with code

Read Also:
Machine Learning Becomes Mainstream: How to Increase Your Competitive Advantage

Randy Bartlett

Randy Bartlett, Ph.D. CAP® PSTAT® is a statistician/statistical data scientist with 20+ years of practice experience analyzing and reviewing data analysis; and leading business analytics teams.He designed 'A Practitioner’s Guide to Business Analytics' to be the foremost reference on how corporations can better implement business analytics and in this era of Big Data.

Blog 8: Statistics Denial Myth #4, Rebranding Predictive Modeling



Big Data and Analytics for Healthcare Philadelphia

off with code

Read Also:
How to Use Data to Create Engaging and Appealing Narratives
Read Also:
Key Technologies Behind Big Data

Randy Bartlett

Randy Bartlett, Ph.D. CAP® PSTAT® is a statistician/statistical data scientist with 20+ years of practice experience analyzing and reviewing data analysis; and leading business analytics teams.He designed 'A Practitioner’s Guide to Business Analytics' to be the foremost reference on how corporations can better implement business analytics and in this era of Big Data.

Blog 8: Statistics Denial Myth #4, Rebranding Predictive Modeling



SMX London

off with code

Read Also:
Predictive Analytics is the Future of Financial Marketing

Randy Bartlett

Randy Bartlett, Ph.D. CAP® PSTAT® is a statistician/statistical data scientist with 20+ years of practice experience analyzing and reviewing data analysis; and leading business analytics teams.He designed 'A Practitioner’s Guide to Business Analytics' to be the foremost reference on how corporations can better implement business analytics and in this era of Big Data.

Blog 8: Statistics Denial Myth #4, Rebranding Predictive Modeling



Data Science Congress 2017

off with code

Read Also:
How to buy data for your business

Leave a Reply

Your email address will not be published. Required fields are marked *