An Overview of VAR Modelling

Judging by the posted comments and the emails I've received, there's no doubt that my various posts on different aspects of VAR modelling have been quite popular.

Many followers of this blog will therefore be interested in a recent working paper by Helmut Luetkephol. The paper is simply titled, "Vector Autoregressive Models", and it provides an excellent overview by one of the leading figures in the field.

You can download the paper from here.

© 2012, David E. Giles

As Good as it Gets!

Last Friday was a pretty good day for one of my grad. students, Ryan Godwin. Not only did he get a job offer for a tenure-track position, but he saw one of his journal articles in print for the first time. It doesn't get much better than that!

An Irish Economic Statistician

Today, of all days, it seems appropriate to mention an outstanding Irish statistician - one who made seminal contributions to "economic statistics", as well as to mathematical statistics. I'm referring to Robert ("Roy") Charles Geary.

Grad. School Rankings for Econometrics

If you're interested in how U.S. graduate economics programs rank when it comes to econometrics, check here.

© 2012, David E. Giles

Goodness-of-Fit Testing With Discrete, Circular, Data

Testing if a sample of data comes form a specific distribution is a central problem in statistics. This sort of "goodness-of-fit" testing is also important in econometrics, of course. Most goodness-of-fit tests involve "comparing" the empirical distribution function for the sample data with an hypothesized theoretical distribution. The tests rely on the Glivenko-Cantelli Theorem, which states that the maximum (vertical)  "gap" between the empirical and theoretical c.d.f.'s will vanish, everywhere on the support of the distribution, as the sample size grows without limit.

Some such tests are based on this "maximum gap", while others are based on the area between the empirical and theoretical c.d.f.'s. Examples of the first type of test include those associated with the names of  Kolmogorov, Smirnov, Kuiper, Watson and Lilliefors. Examples of the second type include the tests of  Anderson and Darling, and Cramér and von Mises. 

All of these tests are available in EViews. You select the series and then choose "View", "Descriptive Statistics & Tests", and then "Empirical Distribution Tests". 

How Not to Use Econometrics!

I loved this post by Eric Crampton on the Offsetting Behaviour blog. Time to call in the Regression Police, methinks!

© 2012, David E. Giles

Forecasting Flowers

Last March I had a post that I titled "Modelling Flowers on the Wall". It was to do with the Great Victoria Flower Count that the people of this town engage early in each Spring in the hope of annoying friends and family living in less temperate parts of our continent.

In that post I developed an extremely sophisticated forecasting model that can be used to predict the flower count each year. The 2012 count is now on, so before the final numbers are in I'd better give you my forecast!

Here it is: 1,573,026,000 blooming flowers.

Oh, I almost forgot - the forecast standard error is 2,451,832,000. I think I'll be O.K.!

(You'll find the data and EViews workfile I used here.)

Postscript (9 March, 2012): The official tally was announced yesterday - 2,043,380,013.

© 2012, David E. Giles

You had to be there!

It was the Fall of 1983. I was on Study Leave from Monash University in Australia, and I was spending about 6 months in the Economics Department  at the University of Western Ontario. My good friend, Aman Ullah, had arranged the visit and I ha a wonderful time.

There were several seminar programs running on a weekly basis, including one in econometrics. Some time that term there was an econometrics seminar presented by two young Assistant Professors in the department. Here is how it went down.

Leap Year Econometrics

I guess there must be a few econometricians who were "leap year babies" - that is, born on 29 February. I'm not one of them, but a former co-author of mine was. This is the first February 29th since he passed away, and it's a good day to remember how much fun we had working together.

A Trick With Regression Residuals

Suppose that you've estimated an econometric model and you want to test the residuals for serial independence, or perhaps for homoskedasticity. The trouble is that for the model and estimator that you've used, your favourite computer package doesn't provide such tests. Is there a quick way of "tricking" the package into giving you the information that you want?