Bad News for Instant Analytics Sharpies

June 28, 2016

I read “Leading Statisticians Establish Steps to Convey Statistics a Science Not Toolbox.” I think “steps” are helpful. The challenge will be to corral the escaped ponies who are making fancy analytics a point and click, drop down punch list. Who needs to understand anything. Hit the button and generate visualizations until somethings looks really super. Does anyone know a general who engages in analytic one-upmanship? Content and clarity sit in the backseat of the JLTV.

The write up is similar to teens who convince their less well liked “pals” to go on a snipe hunt. I noted this passage:

To this point, Meng [real statistics person] notes “sound statistical practices require a bit of science, engineering, and arts, and hence some general guidelines for helping practitioners to develop statistical insights and acumen are in order. No rules, simple or not, can be 100% applicable or foolproof, but that’s the very essence that I find this is a useful exercise. It reminds practitioners that good statistical practices require far more than running software or an algorithm.”

Many vendors emphasize how easy smart analytics systems are to use. The outputs are presentation ready. Checks and balances are mostly pushed to the margins of the interface.

Here are the 10 rules.

Statistical Methods Should Enable Data to Answer Scientific Questions
Signals Always Come with Noise
Plan Ahead, Really Ahead
Worry about Data Quality
Statistical Analysis Is More Than a Set of Computations
Keep it Simple
Provide Assessments of Variability
Check Your Assumptions
When Possible, Replicate!
Make Your Analysis Reproducible

I think I can hear the guffaws from the analytics vendors now. I have tears in my eyes when I think about “statistical methods should enable data to answer scientific questions.” I could have sold that line to Jack Benny if he were still alive and doing comedy. Scientific questions from data which no human has checked for validity. Oh, my goodness. Then reproducibility. That’s a good one too.

Stephen E Arnold, June 28, 2016

Written by Stephen E. Arnold · Filed Under Analytics, Big data, News

Comments

Comments are closed.

Search the site
Subscribe to Beyond Search
Feature archive
News archive

Stephen E. Arnold monitors search, content processing, text mining and related topics from his high-tech nerve center in rural Kentucky. He tries to winnow the goose feathers from the giblets. He works with colleagues worldwide to make this Web log useful to those who want to go "beyond search". Contact him at sa [at] arnoldit.com. His Web site with additional information about search is arnoldit.com.