TRC

Was at Il Tartufo* in Manayunk the other night, waiting near the bar after dinner when a waiter - who was not my waiter - surprised me. "How'd you like the Fettuccine Cinghiale?" she asked.

I had liked it just fine, but was curious to know how she knew what I'd eaten. I hadn't seen her near my table all evening.

"I just saw the bill for your table," she replied. "Guys always get the wild boar pasta."

Part waiter and part analyst - new competition for us market researchers?

Tags: Statistics, misleading statistics

Sometimes as researchers we get too hung up on knowing everything.   We get frustrated by interesting findings that can't be explained with the available data and this can cause us to miss important insights. I suspect that the proliferation of available data will do little to help fill in the blanks...in fact, it might make the problem worse. A simple exercise in text analytics highlights this point.

There are now an array of tools available to help quantify and understand massive amounts of text.  For example,  at one of our conferences last year, Oded Netzer of Columbia University presented an amazing tool that analyses message boards and other online forums to learn about specific markets (slides can be found at:  http://www.trchome.com/research-knowledge/conferences/437). Tools like these provide a rich and valuable source of data, but insight can also be gleaned from far more simple approaches.

Tags: Text Mining, Statistics

The 2012 Presidential Election season is upon us. I don't know about you, but other than the barrage of commercials, the thing I like least about political campaigns is the terrible abuse of numbers. Combined with the current debate on the debt limit and we have the makings of a tsunami of misleading or outright incorrect statistics.

A  few weeks ago, Megan Holstine started a discussion about a Senator using a totally made up statistic. Sadly for him, he quoted a number that was far from accurate, but also one that was easily verified. His defense was that he didn't intend the statistic to be taken "literally".

Makes me wonder if perhaps we've got it wrong.  Think of the possibilities for us if we stopped taking numbers literally!

Tags: Statistics, Market Research, correlation, causation, misleading statistics, politics