Econometrics for the Masses, Blind Boy, and Courage

It must be in the early eighties. I was out of work and trying to find luck offering my help to some very qualified and energetic public health professionals. In a seminar or a meeting of some sort on management information systems, I boldly (or foolishly, depending your point of view) presented a note on GIS for the masses. That was based on some free software which was quite an innovation that time. The expatriate GIS professional who presided surely must have been annoyed though she went on unhindered to develop the system with her pet commercial GIS. Things have changed. Now the die hard supporters of commercial GIS software may have nothing better than to (reluctantly) acknowledge the power of free and open-source GIS software like Grass or QGIS.

So, if not by expertise, then by motivation and by intent I should be allowed to speak about econometrics for the masses. Well, I have tried the like of it before with my posts "An Unclaimed CD on Psychometrics with R or Intro to Anything with R" and "Blind leading the 20/20".

Because, we are woefully like the blind boy I remember from my school-boy days:

"O SAY what is that thing call'd Light,
Which I must ne'er enjoy;
What are the blessings of the sight,
O tell your poor blind boy!"

Any light could have been light enough and you wouldn't expect me to have much expertise to write such as those! And I'm feeling like Courage the Cowardly Dog.

Though, with a bit of soul searching, I realized mine were no better than the idle tales of my wanderings after trying to find my way in unfamiliar places at dusk. Anything goes. With that, I owe an apology to a friend of a friend—who is working in Naypyitaw and who happened to be looking for some econometrics software—if he were to find this post too shallow. I got the inspiration for this post from him.

Econometrics is "the unified study of economic models, mathematical statistics, and economic data. ... Econometric theory concerns the development of tools and methods, and the study of the properties of econometric methods. Applied econometrics is a term describing the development of quantitative economic models and the application of econometric methods to these models using economic data." (Econometrics, Hanson, 2000, revised 2015). In plain English it is "The Economist's Approach to Statistical Analysis" as explained in Econometrics for Dummies.

Groping through search results on the web for econometrics, I noticed a lot of introductory material mentioning Stata as their software for making econometric analyses. The reason is the same as when people casually talk about R vs. SPSS, R vs. SAS, or R vs. Stata. They have in mind the way these other software allow making statistical analysis by using drop-down menus, while R basically does not. Ease of use vs. steep learning curve, if you like.

Karem Tuzcuoglo, a PhD candidate in economics at Columbia explains:

"One-Click" Programs ((almost) no coding required, results obtained by one click)
STATA: Most of the econ undergrad programs use STATA. It is the best program (even at the PhD level) if you want to estimate panel data (i.e., where the data hava both cross sectional and time series dimension. Typical examples are surveys and international trade data sets).
Eviews: Less famous than Stata, but provides much better time series analysis. If you don't want to do time series forget about Eviews.
SPSS: I don't have much information about it. But I can tell that it's not widely used.

"Semi-Coding" Programs
SAS: It used to be a big deal 10-20 years ago. Right now not as famous as before - though there are some companies that still strictly prefer using SAS.
R: Maybe the most popular program nowadays. First of all it's free! R network and R packages (pre-written algorithms by others) are getting larger and larger. Actually, R can be listed in the next section as well because one can definitely code everything in R. However, the fact that there are so many ready-to-use packages in R makes it also Semi-Coding program if one wants to.

"Pure-Coding" Programs
MATLAB: The most famous program among (high level) econometricians. Many applied economics have been done by Matlab. A lot of researchers put their Matlab codes online. It has a good Econometrics package - one still needs to code though.
PYTHON: It's more powerful and faster than Matlab. However, it's a very new language; it's still developing. 
C++: If one wants to do hardcore coding, then C++ is the ultimate program. It's extremely fast in terms of computation (once, my simulation took 25 hours in Matlab, whereas C++ ran the code in 3-4 hours).
FORTRAN: Professors above 55+ age will know this program. It's (almost) not used anymore - though we should show some respect to the Father of Coding Programs!

BONUS: There are several other programming languages of course. If you are in UK (especially in Oxford), you will end up using a program called Ox., which is an optimized program for matrix algebra and, thus, for econometrics.Gretl is an extremely easy to use - but less to offer- program. 

Among all of the options, I would suggest you to learn R regardless of whether you want to work in academia or in industry (more and more companies begin using R by the way). But if you want to stay away from coding, then go for STATA.

    

A good collection of resources is the special volume on Econometrics in R, vol. 27, July 2008, by the Journal of Statistical Software, which is available for download. As usual, the first site to consult relating to R packages would be the CRAN tasks views, and in this case it is the Econometrics Task View available on any CRAN mirror site. Here the description of packages are organized into eight topics: (i) Basic linear regression, (ii) Microeconometrics, (iii) Instrumental variables, (iv) Panel data models, (v) Further regression models, (vi) Time series data and models, (vii) Data sets, and (viii) Miscellaneous. As of now, there are a total of 117 R packages on this task view.

At the end of the econometric task view page, there is a list of useful links. Among them the link for (i) A Brief Guide to R for Beginners in Econometrics took me to the University of Stockholm website and I was lost. Looking for free lunch I followed the link, (ii) Book: Applied Econometrics with R (Kleiber and Zeileis) and found that I've to buy the book. I was so frustrated, I missed the offer for free downloads of some pages of the book at the bottom of the page. Then, (iii) Book: Hands-On Intermediate Econometrics Using R (Vinod) another book you have to buy, allows you to download the foreword and chapter-1.

Luckily and thanks to Dave Giles' blog Econometrics Beat, I was led to the downloadable link to An Introduction to Programming Econometrics With R by Bruno Rodrigues of the University of Strasbourg.

Again I was lucky to find on Giles' post the comment by Achim Zeileis, one of the authors of Applied Econometrics with R (AER) pointing out the free resources accompanying their book: "The book itself is not free (published by Springer) but the first two chapters can be downloaded for free from the publisher and we have free presentation slides/scripts for the whole book plus some extras. Everything is collected online at: http://eeecon.uibk.ac.at/~zeileis/teaching/AER/".

I was aware of, for some time, that one staple reference for intro to econometrics with R has been the Econometrics with R by Grant Farnsworth of 2008.

Finally, I managed to find the A Brief Guide to R for Beginners in Econometrics by Mahmood Arai of Stockholm University at http://homes.chass.utoronto.ca/~jmaheu/4050/R_intro.pdf.

At last, relieved of my self-proclaimed duty to say something about Econometrics for the Masses ..., I could go back to enjoy the Blind Boy. Ever a blind boy, we could still be defiant. The last stanza reads:

"Then let not what I cannot have
My cheer of mind destroy;
Whilst thus I sing, I am a king,
Although a poor blind boy."

And yet, while at the bottom of our heart we knew where we rightfully belong, we shouldn't stop groping for light even when we are in total darkness, shouldn't we? For me, I would love to have this third stanza in place of the last:

"My day or night myself I make
Whene'er I sleep or play.
And could I ever keep awake
With me 'twere always day."