On Random Numbers

These days, we take it for granted that it's very simple, and relatively costless, to generate random numbers. Really, these are "pseudo-random numbers", and we should pay careful attention to the quality of the algorithms that are used to generate them, as I've noted previously (and also here) on this blog.

Putting these qualification to one side, however, we've certainly come a long way from having to rely on that famous tome, A Million Random Digits With 100,000 Normal Deviates. Published by the Rand Corporation in 1955, this classic provided (lots of!) random digits that could be used as an aid to simple random sampling, as well random deviates generated from the standard normal distribution. The latter could be used in Monte Carlo simulations, for example.

The following is an extract from a handout that I use in my introductory statistical inference course:

Sad News

I was sad to learn that John Nankervis passed away on Christmas morning. Well known for his many important contributions to econometrics, John was Professor of Finance and Director of Research in the University of Essex Business School.

John will be greatly missed.

© 2012, David E. Giles

The Greenfield Challenge

The European Network for Business and Industrial Statistics has the objective of "...connecting individuals and organisations, interested in theoretical developments and practical applications in the field of business and industrial statistics." They achieve this through their electronic network, and an annual Spring Conference.

The co-called "Greenfield Challenge", which is now an annual event, arose from a challenge laid down by Tony Greenfield in his George Box Medal acceptance speech in 2009:

"My challenge to you is that you will tell some audience about work you have done, and completed successfully because you used a statistical method. But that audience must be of people who are not statisticians.

And you will have spoken to those people through publications that are for the wider public, through magazines or newspapers, or from a public platform. You might even write a short story or a play.… That is my challenge: Tell the world, outside your circle, of work you have done, and done successfully because you used statistics."

Fighting words!

You can read more about the responses to this challenge from members of the ENBIS community here.



I really like this challenge. It seems to me that it would be equally applicable to the econometrics community.

What do you think?

© 2012, David E. Giles

National Econometricians' Day

The Netherlands has been a power-house of econometrics since day one. Think of Jan Tinbergen's contributions to the birth of the discipline, for instance. 

So, perhaps it will come as no surprise that 5 February 2013 will be National Econometricians' Day, or "LED" (Landelijke Econometristendag), for students of econometrics. Billed as ".... the largest annual career event for econometricians in the Netherlands", the one-day event will be held in Utrecht in 2013. Their slogan - "LED it be your day!"

I've blogged previously (here and here) about another Netherlands-based initiative for students of econometrics - the Econometric Game. This event has gone from strength to strength, and attracts teams of students from all over the world.

It's great to see the extent of organization and involvement among the Dutch students. They have six associations for econometrics students, and these form the Landelijke Orgaan der Econometrische Studieverenigingen (LOES). The individual associations are: Asset | Econometrics (Tilburg University), Econometrisch Dispuut (Erasmus University), Kraket (VU University), SCOPE | Vectum (Maastricht University), VESTING (University of Groningen) and VSAE (University of Amsterdam).

© 2012, David E. Giles

Top Posts for 2012

Here are the "Top Ten" new posts on this blog during 2012. They're ranked in order of popularity (1 = top)  based on page-views:

1. My "Must Read" List (26 September 2012)
2. An Overview of VAR Modelling (23 March 2012)
3. Regression and Causation (4 December 2012)
4. Seminar Attendance: A Pep-Talk for Grad. Students (8 October 2012)
5. Modelling Extremes (16 April 2012)
6. Integrated & Cointegrated Data (5 June 2012)
7. Degrees of Freedom in Regression (12 October 2012)
8. Central Limit Theorems (29 October 2012)
9. Listening to Your Data (31 October 2012)
10. What I Learned Last Week (12 October 2012)

Thanks for your participation and your comments!

© 2012, David E. Giles

Eggnog With an Econometrics Flavour

With Christmas almost upon us I was giving some thought to a seasonally-themed post. The truth is, it's not as easy to produce one with an econometric flavour as you might think.

I suppose we could look at forecasting retail sales for the holiday season; or construct a SUR model for the market shares held by the major courier companies as they deal with all of us last-minute shoppers and givers. But I wanted something that clearly boasts "Christmas" in the title.

Interestingly (or not) there are not that many published applied econometrics papers that fit the bill. A few years ago, however, I struggled to fill this void with a paper I titled, "Testing for a Santa Claus Effect in Growth Cycles". (You can download the working paper version from here.)

The abstract tells the story:

"We examine the seasonal distribution of turning points in the post-war growth cycles of sixteen economies. Using nonparametric tests for distributions on the circle, we cannot reject a uniform distribution for the turning points for most of the countries. In the case of troughs, uniformity is supported for eleven countries, notwithstanding the unusually large number of December or January troughs. This provides evidence against a ‘Santa Claus effect’ in the growth cycle."

This was one of the first papers that I wrote that involved goodness-of-fit testing with "circular" data. You'll find other posts on this general topic here and here, if you're interested. There are a few things I'd do differently if I were writing the Santa Claus paper now - but isn't that always the case?


Reference

Giles, D. E., 2005. Testing for a Santa Claus effect in growth cycles. Economics Letters, 87, 421-426.

© 2012, David E. Giles

Time Series Econometrics Conference

If you're working in Time Series Econometrics, then here's a conference that may interest you.

The next Workshop in Time Series Econometrics is being held in Zaragoza, Spain, in April 2013.

I like the aims of the workshop:

"Time Series Econometrics has been one of the most productive areas in quantitative economics in recent years. Along with the progress in theory and computation, great possibilities for applications have opened up in several economic fields, both for academics and professional practitioners. For these reasons, a group of us who are very devoted to this subject consider that it deserves a more prominent place in both national and international meetings. The main objective of this TSEW is to fill this gap.

TSEW wishes to bring together academics and non-academic professional practitioners working in Time Series Econometrics in Spain, both in the theoretical and applied dimensions.

We hope this I_t meeting does not suffer any structural break with respect to previous events and that we can carry on enjoying a long time series, without sample size problems, with a deterministic trend towards quality, with long memory and with a common factor based on getting together and enjoying our work in such a stimulating area as Time Series. Even so, we should leave room for some stochastic or random elements."

© 2012, David E. Giles

Judea Pearl Wins 2012 Turing Award

My November issue of Amstat News arrived this morning, and I was most interested to see that  ASA member, Judea Pearl, has been awarded the 1012 Turing Award. This is described as "...the most prestigious award in computer science". 

There is an interesting interview with Judea here. In a related piece of news, the ASA has announced a new "Causality in Statistics Education" award:

"The ASA announces a new prize, Causality in Statistics Education, aimed at encouraging the teaching of basic causal inference in introductory statistics courses. The prize carries an award of $5,000 per year. Donated by Judea Pearl, the prize is motivated by the growing importance of introducing core elements of causal inference into undergraduate and lower-division graduate classes in statistics."

Judea's contributions have been the subject of two recent posts (here and here) on this blog.

© 2012, David E. Giles

More on Regression & Causality

Now back in town, I enjoyed seeing this thoughtful blog post from William M. Briggs. It relates to own recent post, Regression & Causation.

This is a big topic, with lots to be said, from various perspectives.
 

© 2012, David E. Giles

Regression & Causation

Recently I read, with interest, a thought-provoking paper by Bryan Chen & Judea Pearl. The paper is titled, "Regression and causation: A critical examination of econometrics textbooks".

Here's the abstract:

"This report surveys six influential econometric textbooks in terms of their mathematical treatment of causal concepts. It highlights conceptual and notational differences among the authors and points to areas where they deviate significantly from modern standards of causal analysis. We find that econometric textbooks vary from complete denial to partial acceptance of the causal content of econometric equations and, uniformly, fail to provide coherent mathematical notation that distinguishes causal from statistical concepts. This survey also provides a panoramic view of the state of causal thinking in econometric education which, to the best of our knowledge, has not been surveyed before."

Some Recent Papers on Granger Causality

My various posts on testing for Granger non-causality seem to have been quite popular with readers of this blog.

 

For example, see here, here, here, here, and also see the Word-Count block in the right side-bar of this page.

 

The literature involving applications of non-causality testing continues to grow, even though it is now 43 years since Granger's seminal paper on the subject.  Regrettably, some of these applications are lacking in various respects, but there are many that are really excellent examples of  applied econometric analysis.

 

Contributions to the various theoretical and methodological issues surrounding the Granger causality literature also continue to emerge. Here are just a few such papers that have emerged in recent months.

• Matthieu Droumaguet & Tomasz Wozniak, 2012, "Bayesian testing of Granger causality in Markov-switchng VARs
• Christophe Hurlin & Elena Dumitrescu, 2012, "Testing for Granger non-causality in heterogeneous panels"
• Yushi Li, 2012, "Estimating long memory causality relationships by a wavelet method
• Joachim Wilde, 2012, "Effects of simultaneity on testing Granger-causality - A cautionary note about statistical problems and economic misinterpretations"
• Tomasz Wozniak, 2012, Granger-causal analysis of VARMA-GARCH models"

These papers cover a lot of important ground, and they're well worth taking a look at if you have an interest in testing for Granger non-causality.

 

  

© 2012, David E. Giles

Assistant Prof. Position at UVic

Not my usual sort of post, I know, but I just wanted to get it out there that my department (Economics, at the University of Victoria, on the West coast of Canada) is looking to hire a tenure-track Assistant Professor. The details of the position are available here.

 

We've only just got permission to hire, so we're really scrambling to catch up with this year's job market. Anything that you can do to get the word out to likely applicants, placement officers, etc. would be a great help to us.

 

Any enquiries should be addressed directly to econfacultysearch@uvic.ca.

 

 

© 2012, David E. Giles