Hard question to your Professor!

From Hugo Domic

The question this week is intended to a Econometrics/Statistics professor, but is funnier (really really funny) to ask to a Macro Professor (as a rule you will never-ever get an answer)

Why everything is supposed to follow a Normal Distribution?

If we were in biology, our pure statistics no problem whatsoever on the use of the Normal Distribution but we study economics!
So when we say that consumption follows a random walk , when we study the Lucas Model and Rational Expectations in general, all the results are a direct and simple result of the assumption of normality on the error term.
But how can this be?
The Normal distribution goes from -infinity to +infinity. So far so good, but economically this means that, e.g. the random walk hypothesis, that we can have a infinitely negative shock on consumption, but even before hitting -infinity the agent would be dead! how can you live with a negative consumption???
Not only that but even if the shock is small (negatively) nothing says we will not have again a negative shock next period! So if I’m not dead this period I will be next period! So we use a model of consumption that don’t even guarantees that we will have any agents alive in the economy! This is simply ridiculous.

Furthermore the Normal distribution supposes that both positive and negative effects happen with the same probability, but from historical data we know that consumption, investment, etc, has more positive periods than negative periods. Thus if we want some reality in economic models is better to impose some power law on the error terms (say Pareto (a special form), or whatever,  almost every other distribution is better suited to study economics than the Normal Distribution.

I believe that the only reason that the normal distribution is so widely used is because Economists don’t understant, don’t want to understand and will not understadt that the mathematics that we impose on our models shape the results. Thus is not only because the result is good for some ideology (mainly Chicago School Ideology) that we should trust the mathematics behind.
And for that we can fully blame Milton Friedman and his essays on Positive Economics.

But now is time to go beyond this simple and unrealistic models and impose conditions that look like the reality that can give us not only better results but can allow us to study the real dynamics on a economic system.

Go Hard on your Professors!

Advertisements
This entry was posted in Hard question for Professors!. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s