4. Stats rules covering 80% of what you'll (probably) ever do

2012-10-02 16:00:54 +0000

I really like Andrew Gelman. He always presents statistics in a straightforward way. One of my favorite blog posts of his is from 2010 (“What do practitioners need to know about regression?”), where he outlines a few simple rules of thumb for doing statistical analysis.

These rules probably cover the vast majority of work you’ll ever need to do. Read them and take them to heart. Then read them again. And post them where you can clearly see them. Below I’ve quoted them, but you can find the original post here.

Without further ado:

The difference between “significant” and “non-significant” is not itself statistically significant.

Don’t just analyze your variables straight out of the box. You can break continuous variables into categories (for example, instead of age and age-squared, you can use indicators for 19-29, 30-44, 45-64, 65+), and, from the other direction, you can average several related variables to create a combined score.

You can typically treat a discrete outcome (for example, responses on a 1-5 scale) as numeric. Don’t worry about ordered logit/probit/etc., just run your regression already.

Take the two most important input variables in your regression and throw in their interaction.

The key assumptions of a regression model are validity and additivity. Except when you’re focused on predictions, don’t spend one minute worrying about distributional issues such as normality or equal variance of the errors.