Sign up | Login with →

Comments by Timo Elliott Subscribe

On Science Needs to Be Less Certain

I get the theory, but really? Science is elitist, for good reason. Do you honestly think there were golden nuggets of scientific truth just waiting to be discovered in those comment sections?  And if there were, did they outweigh the very real dangers of phoney MMR scandals and other mass hysteria that are demonstrably fueled / enabled by such open-yet-misguided debate?

October 21, 2013    View Comment    

On Brain Scans Show No Difference Between Pie Chart and Bar Chart Perception?


It is indeed very hard to be civil when one is attacked!

In the post, I tried to be very careful not to make any claims myself, knowing that discussions of data visualization tend towards the tendentious. Instead, I tried to summarize the format of the experiment, and then quoted the paper's results. Maybe I should indeed have stopped after the abstract:

"In this paper, we use the classic comparison of bar graphs and pie charts to test the viability of fNIRS for measuring the impact of a visual design on the brain. Our results demonstrate that we can indeed measure this impact, and furthermore measurements indicate that there are not universal differences in bar graphs and pie charts."

I further reiterate the advice I gave to readers: "I would encourage you to spend as much time understanding what’s interesting about the study as you spend trying to figure out why you can disagree with it"

Next: my attempt to "discredit you" and "undermine your credibility". You seem to be including this post as an example, which I find very strange, since I call you an expert, quote your book, and call your example "compelling" -- and there is no trace of irony. 

January 29, 2013    View Comment    

On The Use and Abuse of Big Data

You're the one that proposed just "contemplating!" :-)

The missing conclusion: people need to be "saved from themselves", saved from giving away too much data for convenience. This is what government is for. It's just like consumer protection law or even car seat belts... Strong privacy laws are needed, Europe is much further ahead on this that the US.

January 28, 2013    View Comment    

On The Use and Abuse of Big Data

The Economist said many years ago "privacy is dead," remarking that the only reason we didn't yet feel the effects was because of data quality and integration problems...

January 24, 2013    View Comment    

On Analytics: Not About Saving Time

Completely agree. Extra speed is only really important when you cross a threshold that can change the way you do things (e.g. provide cancer analysis to a patient before they leave the appointment). I believe the only useful definition of "real time" is "fast enough to make a difference to the business"...

July 27, 2012    View Comment    



One other big potential BI benefit is reducing risk. It's hard to measure, but it has the potential to outweigh all the others, especially in the current turbulent times. 

I often like to say that "information is useless unless it's used to change something in the business", but my wife (a lawyer) recently corrected me. She's in the business of reducing contractual risks, and pointed out that knowing that nothing bad has happened can also be very valuable -- i.e. it's not always about the upside: real life involves avoiding or minimizing the downsides, too... 

BI Questions blog:
February 26, 2009    View Comment