Wednesday, May 4, 2016

My Latest Paper About Dummy Variables

Over the years I've posted a number of times about various aspects of using dummy variables in regression models. You can use the "Search" window in the right sidebar of this page if want to take a look at those posts.

One of my earlier working papers on this topic has now been accepted for publication.

The paper is titled, "On the Inconsistency of Instrumental Variables Estimators for the Coefficients of Certain Dummy Variables". Here's the abstract:
"In this paper we consider the asymptotic properties of the Instrumental Variables (IV) estimator of the parameters in a linear regression model with some random regressors, and other regressors that are dummy variables. The latter have the special property that the number of non-zero values is fixed, and does not increase with the sample size. We prove that the IV estimator of the coefficient vector for the dummy variables is inconsistent, while that for the other regressors is weakly consistent under standard assumptions. However, the usual estimator for the asymptotic covariance matrix of the I.V. estimator for all of the coefficients retains its usual consistency. The t-test statistics for the dummy variable coefficients are still asymptotically standard normal, despite the inconsistency of the associated IV coefficient estimator. These results extend the earlier results of Hendry and Santos (2005), which relate to a fixed-regressor model, in which the dummy variables are non-zero for just a single observation, and OLS estimation is used".
You can download the final working paper version of the paper from here.

The paper will be appearing in an upcoming issue of Journal of Quantitative Economics.


© 2016, David E. Giles

Monday, April 11, 2016

Improved Analytic Bias Correction for MLE's

Ryan Godwin and I have a new paper - "Improved Analytic Bias Correction for Maximum Likelihood Estimators". You can download it from here.

This paper proposes a modification of the Cox-Snell/Cordeiro-Klein bias correction technique that we've used in our earlier research (including work with Helen Feng and Jacob Schwartz). For some more information about that work, see this earlier post.

© 2016, David E. Giles

Friday, April 8, 2016

The Econometric Game Winners

The results of the 2016 edition of The Econometric Game are now out:

1st. Place: Harvard University
2nd. Place: Warsaw School of Economics
3rd. Place: Erasmus University

Congratulations to all of the competitors, and to the organisers of this important event!

© 2016, David E. Giles

The Econometric Game Finalists

The Econometric Game is drawing to a close for 2016. With just hours to go the teams that are completing the final round of the competition are:

Lund University
Warsaw School of Economics
McGill University     (go Canada!)
University of Copenhagen
ENSAE
Aarhus University
Erasmus Universiteit Rotterdam
Harvard University
University of Rome Tor Vergata
University of Antwerp

The case for this year's event is discussed here.

© 2016, David E. Giles

Wednesday, April 6, 2016

The Econometric Game - Update

From the website of The Econometric Game

Revealing of the Econometric Game Case.
Today at the grand opening of the Econometric Game:
The case makers have revealed this year's theme: Socioeconomic inequity in health care use among elderly Europeans.
The case makers Pilar García-Gómez and Teresa Bago d'Uva have worked very hard on designing the case and are looking forward to the results of the participating students. Tomorrow evening the finalist will be announced.

© 2016, David E. Giles

Monday, April 4, 2016

The Econometric Game, 2016

Last December I posted about the upcoming 2016 round of The Econometric Game.

You'll find links in that post to other posts in previous years.

Well, the Game is almost up on us. If you're not familiar with it, here's the overview from  the EG website:
"Every year, the University of Amsterdam is hosting the Econometric Game, one of the most prestigious projects organized by the study association for Actuarial Science, Econometrics & Operational Research (VSAE) of the University of Amsterdam. The participating universities are expected to send delegations of four students majoring in econometrics or relevant studies with a maximum of two PhD students. The teams will be given a case study, which they will have to resolve in two days. After these two days the ten teams with the best solutions will continue to day three. On the third day the finalists have to solve a second case while the other teams can go sightseeing in Amsterdam. After the teams have explored the city, the Econometric Game Congress takes place. There are different interesting lecturers, who will speech about the case and the econometric methods necessary for solving the case. The solutions will be reviewed by a jury of qualified and independent professors and they will announce the winner of the Game. 
The Econometric Game 2016 will take place on the 6th, 7th and 8th of April 2016 in Amsterdam."

I'll comment on the results in due course.

© 2016, David E. Giles

Friday, April 1, 2016

My new Paper

I'm really pleased with the way that my recent paper (with co-author Al Gol) turned out. It's titled "HotGimmer: Random Information", and you can download it here.

Comments are welcomed, of course..........

© 2016, David E. Giles

Saturday, March 26, 2016

Who was Shirley Almon?

How often have you said to yourself, "I wonder what happened to Jane X"? (Substitute any person's name you wish.)

Personally, I've noticed a positive correlation between my age and the frequency of occurrence of this event, but we all know that correlation doesn't imply causality.

Every now and then, over the years, I've wondered what happened to Shirley Almon, of the "Almon Distributed Lag Model" fame. Of course I should have gone to the internet for assistance, but somehow, I never did this - until the other day.......

Friday, March 25, 2016

MIDAS Regression is Now in EViews

The acronym, "MIDAS", stands for several things. In the econometrics literature it refers to "Mixed-Data Sampling" regression analysis. The term was coined by Eric Ghysels a few years ago in relation to some of the novel work that he, his students, and colleagues have undertaken. See Ghysels et al. (2004).

Briefly, a MIDAS regression model allows us to "explain" a (time-series) variable that's measured at some frequency, as a function of current and lagged values of a variable that's measured at a higher frequency. So, for instance, we can have a dependent variable that's quarterly, and a regressor that's measured at a monthly, or daily, frequency.

There can be more than one high-frequency regressor. Of course, we can also include other regressors that are measured at the low (say, quarterly) frequency, as well as lagged values of the dependent variable itself. So, a MIDAS regression model is a very general type of autoregressive-distributed lag model, in which high-frequency data are used to help in the prediction of a low-frequency variable.

There's also another nice twist.......

Tuesday, March 1, 2016

March Reading List

Now is a good time to catch up on some Econometrics reading. Here are my suggestions for this month:

  • Carrasco, M. and R. Kotchoni, 2016. Efficient estimation using the characteristic function. Econometric Theory, in press.
  • Chambers, M. J., 2016. The estimation of continuous time models with mixed frequency data. Discussion Paper No. 777, Department of Economics, University of Essex.
  • Cuaresma, J. C., M. Feldkircher, and F. Huber, 2016. Forecasting with global vector autoregressive models: A Bayesian approach. Journal of Applied Econometrics, in press.
  • Hendry, D., 2016. Deciding between alternative approaches in macroeconomics. Discussion Paper No. 778, Department of Economics, University of Oxford.
  • Reed, W. R., 2016. Univariate unit root tests perform poorly when data are cointegrated. Working Paper No. 1/2016, Department of Economics and Finance, University of Canterbury.

© 2016, David E. Giles