Hypothesis: Autocracies are more likely to fail than democracies.

Â

1. Obtain a large sample of democracy and autocracies over multiple years each

Â

2. Count the number of state failures in each

Â

3. Compare the means

1. Probably omitted variable bias

2. Maybe the difference is just random noise?

- Identify key omitted variable
- Measure it for all country-years
- Calculate it's unique correlation with state failure
- See if there is stillÂ unique correlation of democracy and state failure

**When you do this with many cases using statistics, it's Large-N Observational Research****When you do this with a few cases "manually," it's called Small-N Observational Research**

- Calculate the standard error.
- "Standard error" is equal to standard deviation divided by the square root of the total number of units in the group.
- Check whether the error bars overlap.
- If they don't, it's a statistically significant difference (not reducible to random noise).