Homework1 - Homework # 1 ECO 7427 Prof. Sarah Hamersma Due...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Homework # 1 ECO 7427 Prof. Sarah Hamersma Due Tuesday January 30, 2005 1. Two important concerns with calculating the correct standard errors in the context of measuring treatment effects are: 1) dealing with autocorrelation of the dependent and treatment variables and 2) dealing with the potential correlation of errors within cells (such as within states, when dealing with state-level treatment like a law). We discussed the first one in ECO7424, so I will be asking you to think more about the second one, which (as you will recall) is typically solved by “clustering.” There has been some controversy about whether a correction for correlation of errors within states is needed in the research being done by John Lott on crime issues. In particular, he has recently removed the “cluster” command from his analysis of the relationship between gun laws and crime. This has allowed him to report his results with some precision, but some have argued that these standard errors are incorrect (artificially small). On John Lott’s website he offers a defense of his decision to do his analysis without clustering. http://johnrlott.tripod.com/other/ClusterDebateReconsidered.html I would like you to tell me if this is a sufficient argument for choosing not to use clustering in the analysis. Do your best to convince me of your position by explaining why the analysis does or does not need clustering. To help you, you may need to skim parts of Lott’s papers to understand more clearly what he is estimating (you should be able to find them on his web page or elsewhere online). You may also want to take a careful look at the short Moulton (1990) paper and also at a finance paper by Mitch Peterson available on his website at http://www.kellogg.northwestern.edu/faculty/petersen/htm/papers/standarderror.pdf 2. A lot of good data for economic research is available on the Web. Microdata that are collected by the U.S. Census Bureau are available online, and you can actually choose the particular data you want to extract from larger samples. You will begin this problem by going to the Current Population Survey website ( http://www.bls.census.gov/cps/ ) . It’s useful if you read some of the “overview” material and any other material that might be of interest to you. When you feel you have a sense of what the survey is about, choose “Data” and then, at the top of the page, “Data access via
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/10/2011 for the course ECON 7427 taught by Professor Hamersma during the Spring '06 term at University of Florida.

Page1 / 3

Homework1 - Homework # 1 ECO 7427 Prof. Sarah Hamersma Due...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online