Working as a Statistician at Google

If you love doing empirical work, you've probably wondered what it's like to work at an organization such as Google, where the term "Big Data" takes on a whole new meaning.

If so, you'll enjoy reading Jeff Leek's "Interview with Nick Chamandy, statistician at Google", on the Simply Statistics blog. Nick provides some interesting insights into the life of the statisticians/data analysts at Google, and the culture surrounding their work.

Here are a few excerpts:

"When posting job opportunities, we are cognizant that people from different academic fields tend to use different language, and we don’t want to miss out on a great candidate because he or she comes from a non-statistics background and doesn’t search for the right keyword. On my team alone, we have had successful “statisticians” with degrees in statistics, electrical engineering, econometrics, mathematics, computer science, and even physics. All are passionate about data and about tackling challenging inference problems." ..................................

"Our data sets contain billions of observations before any aggregation is done. Even after aggregating down to a more manageable size, they can easily consist of 10s of millions of rows, and on the order of 100s of columns." ......................

"In the vast majority of cases, the statistician pulls his or her own data — this is an important part of the Google statistician culture. It is not purely a question of self-sufficiency. There is a strong belief that without becoming intimate with the raw data structure, and the many considerations involved in filtering, cleaning, and aggregating the data, the statistician can never truly hope to have a complete understanding of the data."  .........................

I definitely approve of that philosophy.

Enjoy!

© 2013, David E. Giles

I Think It's Them!

The other day I was refereeing a paper, and I thought back to an earlier post from April of last year - "Is it Me or is it Them ??"

'Reminiscing', you say?

Hardly - it's just that I'm still reading far too many empirical (usually micro.) papers in which the econometric "analysis" leaves me shaking my head.

I'm not going to repeat the previous post (you can read it for yourselves), and I certainly can't afford another session with Jane right now.

However, I'm pleased to be able to report that I do think I'm making some progress with my issues!

I've decided that it's not me - it's them!

(That feels better.)

© 2013, David E. Giles

N.Z. Econometrics Study Group

Later this month I'll be participating at the 23^rd annual meeting of the New Zealand Econometric Study Group. As is often the case, the meeting is being held in Auckland - specifically at the University of Auckland.

The NZESG was spear-headed by Yale-based New Zealander Peter Phillips, and he's done a huge amount over the years to promote the continued excellence of the N.Z. econometrics scene.

At this month's meeting I'll be talking about some of my joint work (with Helen Feng and Ryan Godwin) on bias reduction in the context of maximum likelihood estimation. (See here for more on this topic.) It seems I'm also chairing a session and discussing a Peter's presentation of his paper, "On Confidence Intervals for Autoregressive Roots and Predictive Regression ".

It's been quite a while since I was able to get to an NZESG meeting, so I'm really looking forward to catching up with old friends, and seeing what's happening with the always-flourishing N.Z. econometrics community.

I'll report further on this on my return from New Zealand.

© 2013, David E. Giles

Befriend a Book

Books are pretty special to most academics - and to many, many other readers as well. Some of us are especially interested in old books whose very publication tells the story of the history and development of our discipline.

For example, I'm pleased to own copies of Aitken (1942), Aitken (1949), and (courtesy of a former grad. student) Turnbull and Aitken (1932). Some years ago, in Australia, I had some luck at a garage sale and picked up terrific copies of Karl Pearson's Early Statistical Papers (edited by his son, Egon Pearson, in 1948), The Selected Papers of E. S. Pearson, and Contributions to Mathematical Statistics. The latter volume comprises a large number of R. A. Fisher's papers, edited by W. A. Shewhart in 1950.

In 2009, the Royal Statistical Society began a program that they called "Befriend a Book". The objective is to raise funds to assist in the conservation of important books in the historical collection held by the Society.

The latest (February, 2013) issue of the RSS Newsletter contains an item that describes the progress that's being made with "Befriend a Book". For example, the first book to be restored was a copy of de Moivre's The Doctrine of Chances (1838). There are also some interesting pictures of old books. (At least, I found them to be interesting!)


References

Aitken, A. C., 1942.  Determinants and Matrices, 2nd. ed.. Oliver and Boyd, Edinburgh.

Aitken, A. C., 1949, Statistical Mathematics, 6th. ed., Oliver and Boyd, Edinburgh.

Turnbull, H. W. & A. C. Aitken, 1932, An Introduction to the Theory of Canonical Matrices, Blackie & Son, London. 

© 2013, David E. Giles

Granger Causality

It's interesting, to me, that the posts on this blog that have received (and continue to receive) the most hits are those relating to Granger causality. Or, more correctly, testing for Granger non-causality.

The top one of all time remains, "Testing for Granger Causality". (Maybe it's the catchy title?) Then, just behind "How Many Weeks Are There in a Year" (which has nothing to do with causality - at least, not in any  obvious sense), comes "VAR or VECM When Testing for Granger Causality?"

Moreover, in addition to the many comments/questions that are published with those posts, I get numerous emails on this topic - almost on a daily basis.

Of course, some of these are pretty predicable - essentially, they are asking me to do give them a research project; tell them how to write their paper; or else they want to me to tell them how to complete an assignment for some course they're taking!

But then there are the many, many thoughtful emails that ask interesting questions, and raise all sorts of issues that get me thinking. I really enjoy responding to as many of these as I can manage.

So, I've been thinking.

Is there a demand for a short monograph on testing for Granger causality, with the emphasis on the practice, not the theory. In other words, a "how to do it properly" book for non-specialists, with lots of real-data examples.

Any thoughts on this?

• Is there a need?
• What format should it take - printed or e-book?
• Does this sounds like something that might interest you and/or your students?

I'll be interested to see your feedback.

© 2013, David E. Giles

How Many Econometricians Does it Take?

In the December 2012 issue of Significance, a monthly magazine now published jointly by the American Statistical Association and the Royal Statistical Society, there's an interesting article titled, "Statistics of Statisticians: Critical Masses for Research Groups".

In this article, Ralph Kenna and Beretrand Berche discuss the idea of critical mass when it comes to the size of research groups in various disciplines. They explain how the so-called "Ringelmann effect" in sociology can be tested, and how this leads to measures of an upper bound on group sizes, "... above which research quality either tends not to improve or the rate of improvement starts to level out."

ÊSTIMATE

ÊSTIMATE stands for "Early Summer Tutorial In Modern Applied Tools of Econometrics" - the title of a course to be run by the Econometrics group at Michigan State University between 31 May and 2 June this year.

The instructors will be Jeff Wooldridge and Tim Vogelsang, and the topics to be covered are:

Zamzar

Here's a site that I use quite a lot: Zamzar.

Zamzar allows you to upload a file in one format, and they convert it for free to a new format of your choice. You don't have to download and install any software on you own machine. All you need is the original file and an email address.

This morning, for example, I used Zamzar to convert a .emf file to a .gif file. Quick and easy!

© 2013, David E. Giles

Sums of Random Variables

I'm currently teaching first-level course in statistical inference for  (mostly) economics students. They've taken a one-semester course in descriptive (economic) statistics, and now we're dealing with sampling distributions, estimation, hypothesis testing, and simple regression analysis.

Statisticians in History

Today is the birth date of Gertrude M. Cox (1900 - 1978).

The American Statistical Association has a web site titled, "Statisticians in History". The section of that site that I especially like is the one that provides biographical information about a number of influential statisticians.

Students of econometrics will find a wealth of interesting material in many of these bios. It`s always fun to "put a face to the name", and in a sense, this is one way to do it. So, yes, Gertrude Cox was born on 13 January 1900. She was the first Chair of the Department of Experimental Statistics at N.C. State. Read her bio., and you'll see for yourself what a pioneer she was.

Other entries that I especially recommend are those for Herman Hollerith, Jerzy Neyman, and John Tukey.

My personal favourite (for reasons that will be clear from earlier posts - here and here) is the interview with Arnold Zellner.

Enjoy!

© 2012, David E. Giles