Experimenting with economics

Until very recently, I was certain that economics had something to do with money. I didn't know what, because it was never clear to me why business schools needed to cover money in so many different ways-- finance, accounting, economics, marketing..., but I knew without a shadow of a doubt, that economics had something to do with money.
Then I read Freakonomics (it's a good, quick read, even if I don't agree with all his conclusions), and realized that I had no clue what economics is.

Here's a definition from Wikipedia's entry on Economics:

Economics, as a social science, studies human choice behavior and how it affects the production, distribution, and consumption of scarce resources. Economics studies how individuals and societies seek to satisfy needs and wants through incentives, choices, and allocation of scarce resources. Alfred Marshall in the late 19th century informally described economics as "the study of man in the ordinary business of life".

So, economics can be about how people spend their money, but it can also be about how they make other choices (Freakonomics discusses how parents name their children, among other things).

Lately, we've started watching the tv show "Deal or No Deal". It's a very simple game-- there are set dollar amounts hidden in each of 26 cases, ranging from $0.01 to $1,000,000. The contestant eliminates cases one by one, and is periodically offered cash by "the banker" in exchange for stopping. Theoretically, if a contestant eliminates all but one case, he or she gets the value in that case. It is an ideal case for studying economics, so much so that (also from Wikipedia):

A team of economists - Post, Van den Assem, Baltussen & Thaler (report) - have analyzed the decisions of people appearing in Deal or No Deal and found, among other things, that contestants are less risk averse when they have seen their expected winnings tumble. "Losers" tend to continue playing the game even if this means rejecting bank offers in excess of the average of the remaining prizes. A separate experimental study (report) with student-subjects playing the game with scaled down prizes reveals a similar pattern. The findings provide support for behavioral economists, who claim that the classical expected utility theory falls short in explaining human behavior by not accounting for the context of decisions. The study of the four economists is unique, for the underlying "experiment" Deal or No Deal is characterized by high stakes, a transparent probability distribution and only simple stop-go decisions that require minimal skill or strategy.

Here is how we like to watch it: we tivo it, so we can skip commercials and chit chat. Then we track the expected value (the average value) of the remaining cases in excel and compare that to the banker's offer. Pearsonified says that a contestant should accept any offer over the expected value. I disagree, I believe that the opportunity to play is so valuable, stopping while there are lots of cases (including at least 2 high value cases) still in play, is a mistake. I want to calculate the offer value you're likely to get meet or exceed in all but the worst case scenario (eliminating, say, the worst 10%). I'll update the post when I have made the calculation.

Learning new things is fun!