Lecture21DoingAppliedEconometrics - Lecture 21 Doing...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Lecture 21 – “Doing” Applied Econometrics Throughout this course I have attempted to give you a good grounding in the theoretical and applied aspects of econometrics at what amounts to an “advanced beginner” level. Though we have touched on some theoretical topics, we have not delved deeply into this arena in an effort to focus on the “doing” of econometrics. The data that you recently had fun with on your take home exam is an example of some of the problems you can run into when doing econometrics. There is a world of difference between applied and theoretical econometrics. In this course you have been taught a wide variety of econometric techniques but our focus has been on the mechanics of estimation and testing with the exception of the midterm where you were asked to apply what you had learned to a data set with issues that were not identified for you. It is unfortunate that you cannot follow a simple cook book approach to estimate any/every model you might wish to in any/every situation. What I hoped to do in this course is to give you a good basis in theory, and a good understanding of the methods by which you can address “bad” things that happen in the estimation process. Identifying these issues will now be up to you. I do not call myself an econometrician. Perhaps I am merely an economist with above average analytical skills. Perhaps the truest statement is that I am an unapologetic empiricist. I find that the data will usually tell us what we need to know if only we are willing to listen, rather than torturing it into confessing crimes it did not commit. So, I leave you with some advice that is due in large part to Peter Kennedy; The Ten Commandments of Applied Econometrics. Rule 1. Use Common Sense (and economic theory). Common sense is not all that common. A common sense approach does not necessarily require complicated econometric techniques. An example would be the selection of a functional form for your model that corresponds with the requirements of economic theory (e.g. homogeneity, returns to scale, technical change). Also, don’t infer confuse causation from correlation.
Background image of page 1

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

View Full DocumentRight Arrow Icon
Rule 2. Avoid Type III errors. A type III error occurs when a researcher produces the right answer to the wrong question. A corollary of this rule is that an approximate answer to the right question is worth a great deal more than a precise answer to the wrong question. This issue here is that the relevant objective/hypothesis/specification may be completely different from what is initially suggested. Ask questions, especially seemingly foolish questions to ensure that you have a full understanding of the context of the problem. Be sure that you have formulated your approach to the research question appropriately. Rule 3. Know the Context
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 09/12/2010 for the course GERAS 099876f taught by Professor Gtewewa during the Spring '09 term at Aberystwyth University.

Page1 / 9

Lecture21DoingAppliedEconometrics - Lecture 21 Doing...

This preview shows document pages 1 - 3. Sign up to view the full document.

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