Exogenous variation

Colonies in the 19th century first stage regressions

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: k + u In acemoglu, institutions are X, growth is Y, settler mortality is Z (does not affect growth directly, but through institutions) Step 1, is to see if Z affects X Step 2: Y=b0+b1X+e Substitute the fitted X in place of the original X Fitted X means all the values along the line (and not the individual X values) Two- stage least- squares (2sls) First stage: current economic institutions = f1(settler mortality Second stage: current log income per capita = f2(current economic instituions) There are data on mortality rates of soldiers stations in the colonies in the 19th century First stage regressions of settler mortality vs. Dependent variable is protection against risk of expropriation Settler mortality and risk of expropriation is negative, so as settler mortality increases, the protection against risk of expropriation decreases. The farther away from the tropics, the better off protection...
View Full Document

This document was uploaded on 03/28/2014 for the course INAF 252 at Georgetown.

Ask a homework question - tutors are online