»Me, myself and BI«

Bissantz ponders


Friday, June 8th, 2007

Death to the ritual of significance tests!

If you claim that something is “statistically significant”, your audience will usually be all ears. For many people the term signalizes a type of soothing assurance. We contend that significance is not a matter of coincidence but simply what we wanted to measure in the first place. Misinterpretations of significant results are common. At the end of the day, you need to make your own conclusions. There are no statistical methods that can do this for you.

Friday, May 18th, 2007

The scale is your message

Chopping the axes of a graph is one of the most common forms of data manipulation. Stretching or squishing the scale is equally taboo. However, different scales might have their validity in certain situations.

Friday, March 23rd, 2007

Ivy League Rock and Roll – A day with Edward Tufte

Edward Tufte, the world’s most renowned visualization expert, holds legendary information design seminars up to 40 times a year. What an experience!

Tuesday, May 9th, 2006

Rules of Quotation

When faced with the task of saying something smart about statistics in general, we often find ourselves quoting great people. There’s a well known remark by Winston Churchill that is particularly popular. The editor-in-chief of a important business newspaper used it recently, just as many others have in the past. He had to write an introduction to a highly useful compendium packed with statistics related to international numbers that was being published by the same company. To emphasize the quality of the data gathered in the book, he referred to Churchill, trying to reassure him post-humously by saying that the data came from absolutely trustworthy sources and that he would certainly have appreciated the potentially surprising connections the book comes up with.

The problem is that this well-known saying isn’t Churchill’s at all, but was attributed to him by Joseph Goebbels.

Anyone still wanting to use dead British statesmen to bolster their arguments are better off finding someone else. Benjamin Disraeli, for example, coined the equally oft-quoted “There are three kinds of lies: lies, damned lies and statistics.” Or at least, Mark Twain claims Disraeli said it. Plenty of others attribute it to Twain himself.

Essays

Death to business charts!
Why business charts must die

Graphic tables
Lay back and control

Industrial reporting
Production-like efficiency for management reporting

Can we drive companies
like we do cars?

Against dashboards, speedometers and traffic lights in Controlling

Business Intelligence 2.0
modest, serious, sincere

Rediscovering slowness
Sparklines make us John Franklins in management information.

Good reporting is boring
Looking for excitement?
Try a night on the town instead.

Are sports fans smarter
than managers?

Management reports need to become more dense and dashboards more rare

The myth of data mining
Why men don't buy beer and diapers at the same time.

Numerical blindness?
I wouldn't see a doctor, if I were you.