Pset5S07v1

Pset5S07v1 - the text book, adding as explanatory variables...

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

View Full Document Right Arrow Icon
Economics 166 Spring 2007 Prof. Joseph G. Altonji Problem Set 5: Difference in Differences and Fixed Effects Due Thursday, April 5th, in class 1. Use the data in injury.dta for this exercise, which contains the data used by Meyer, Viscusi and Durbin. Note that seven dummy variables are included for various injury types. They appear to have been created from the variable injtype, which takes on 8 values. You can create a dummy for the omitted category, other diseases, by subtracting the sum of the 7 dummies from 1 if you feel you need it. (You shouldn’t). The dummy variable for ``other industries’’ is excluded from the data set, but you can create if you need it. (You shouldn’t.) (This problem is drawn in part from Wooldridge.) (i) Using the data for Kentucky, re-estimate equation (13.12) in
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: the text book, adding as explanatory variables male, married , and a full set of industry and injury type dummy variables. How does the estimate on afchnge-highearn change when these other factors are controlled for? Is the estimate still statistically significant? Compare your results to Table 6, column 1 of Meyer et al. Do they match closely? (ii) Estimate equation (13.12) using data for Michigan. Compare the estimates on the interaction term for Michigan and Kentucky. Is the Michigan estimate statistically significant? What do you make of this? In particular, is it correct to interpret the evidence as suggesting the workers in Kentucky respond to the generosity of workmans compensation while workers in Michigan do not? 2. Wooldridge C14.4...
View Full Document

Ask a homework question - tutors are online