Prof. Bryan Caplan

http://www.gmu.edu/departments/economics/bcaplan

Econ 345

Fall, 1998

Week 10: Endogenous vs. Exogenous Variables

- Endogenous vs. Exogenous
- Statistics by itself just gives correlation, but usually causation is what is interesting.
- Exception: Forecasting.
- There are many techniques you can try to see if a relationship is causal or merely correlation.
- Controlling for other variables.
- Adding trends to the list of regressors.
- Double-checking your results using multiple data sets.
- However, all of these techniques are imperfect. To get truly clean results, you need double-blind controlled experiments.
- When your data come from double-blind, controlled experiments, your independent variables will be "exogenous." Literally, this means that the independent variables are determined "outside the system" - i.e., by
*you*, the researcher. - On the other hand, when your data do not come from double-blind controlled experiments, you independent variables
*may*be "endogenous." Literally, this means that the independent variables are determined "inside the system." This means that the "dependent" variable may in fact be causing the "independent" variables, and not vice versa. - However, data not derived from double-blind controlled experiments don't
__have to be__endogenous; the danger is merely that they*could be*. Even if you don't set up a double-blind controlled experiment yourself, there is the possibility that historical data supplies you with a__natural__experiment, or something close to a natural experiment. - Some examples of natural experiments:
- The Great Contraction
- German hyperinflation
- Twin studies
- Illustration of the Problem
- Disease and treatment
- Anticipated inflation and monetary policy.
- War and economic growth
- Elections and economic growth
- Mathematical example #1: suppose that inflation=money supply growth -2% + N(0,2); suppose further that the Fed sets money supply growth so that inflation=2%. Then you observe no correlation between money and inflation, even though there is a direct causal link!
- Mathematical example #2: suppose that disease fatality rate = 5%-treatment dosage+5%*severity. Severity ranges from 0 (not sick) to 5 (most sick). Suppose further that treatment dosage=2.5%*severity. Then it appears that disease fatality rate=5%+treatment dosage!
- Picking Exogenous Variables
- The best source: go to the historical record.
- Non-human (e.g. weather)
- Famines under Communism
- Human (e.g. shifts in ideology)
- The Great Contraction
- Hyperinflations
- Fed announcements and the Romer dummies
- In general: the more latitude/discretion an agent has, the more you can learn about the causation.
- Resolving the Problem of Correlation vs. Causation
- First best: Do double-blind controlled experiment. (Sometimes actually done: experimental economics is a growing field).
- Second best: Find approximate natural experiment.
- Third best: Control for any plausible omitted variables and/or add trend variables.
- Fourth best: Present with a warning.
- A big plus: Have a good theory to start with.

Next 4 weeks: Applications.