Learn to run the figures

- Introductory Econometrics Using Monte Carlo Simulation with Microsoft Excel. First Edition
- Introduction to Econometrics. Third Edition
- Empirical Dynamic Asset Pricing. First Edition

May 25, 2007

In 1970, when I was a first-year undergraduate social scientist, my elementary statistics course required me to write a program in Fortran.

As I recall, it computed and printed out the average of ten numbers. With a typical 24-hour delay between submitting the deck of painstakingly punched IBM cards and receiving the output on big sheets of listing paper, debugging was a protracted business, but I still recall the pleasure of getting back the first clean output with the correct answer printed, instead of indecipherable error messages.

Back then it was assumed that programming skills would become de rigueur for economists and social scientists, but things have not quite worked out that way. Nowadays, "computer skills" usually means knowing what the Windows Start button is for. It is unusual to meet an economics student who has even heard of Basic, never mind learnt it. Notwithstanding the computing revolution of the past 30 years, it remains difficult to show students the methods and formulae of econometrics in action in an enlightening way.

Part of the problem is that things have become too complicated, but the way econometric software has developed has not made matters easier for teachers. Commercial packages developed for research are idiosyncratic in design and very expensive. The humble spreadsheet is still the most accessible means to study and manipulate data. Few computers do not have Excel or suchlike, and, if a student today were given an exercise comparable to mine, the spreadsheet would be the natural vehicle for it.

Off the shelf, spreadsheets have their limitations, lacking many of the functions required in modern econometrics. They can, however, run macros of unlimited complexity. Humberto Barreto and Frank Howland's Introductory Econometrics Using Monte Carlo Simulation with Microsoft Excel is an admirable attempt to apply spreadsheet programming to a pedagogical purpose. The book has a CD insert, and the amount of editorial material on this matches that contained in the book. There are 24 chapters and several spreadsheets associated with each, often containing substantial amounts of explanatory text. When loaded into Excel, the exercises look clear and well designed, and those I tried performed correctly. But the sheets tend to be large and complicated.

By its nature, the material is focused on independent study, and the ideal user of this book would perhaps be a well-motivated distance learner, making his or her own progress through the exercises. The book could certainly be used successfully for undergraduate teaching, although the instructor would need to invest a good deal of effort in preparation. The material will need some digestion and a careful selection of topics to fit a one-semester regression course. The authors claim that practical illustration of econometric concepts allows a less mathematical treatment, but this book will not spare students a thorough understanding of the intricacies of Excel. I for one have learnt quite a lot about its capabilities just by playing with some of these exercises. No harm in that, perhaps.

A contrast in styles is provided by Christopher Dougherty's Introduction to Econometrics , now in its third edition. This has been developed from the course delivered by its author, over many years, to second-year economists at the London School of Economics. It has become a well-honed system for the delivery of difficult material to non-specialist students.

In this text, too, computing by the students represents an important and integral part of the teaching. Exercises are built around the Stata and EViews packages, the former for cross-section analysis and the latter for time series. The connection between theory and practice is emphasised in the text by reproducing tables of output created with these packages. Of course, most students can use such packages only with the benefit of an institutional site licence, and unfortunately cannot take the exercises home on their laptops.

The books are not entirely comparable, since Dougherty's is pitched at a somewhat higher technical level, extending to topics such as cointegration and panel data. I tend to prefer his approach to various topics, although Barreto and Howland's is clearly written, with interesting asides, quotations and anecdotes. Both books tackle the difficult task of teaching those often reluctant recruits to compulsory "quants" modules for economists. The authors have invested much effort to capture the imagination of their readers. Noting that the books are targeted at slightly different audiences and learning settings, I can warmly recommend both.

About as far from these two introductory texts as it is possible to go is Empirical Dynamic Asset Pricing by Kenneth Singleton. This is for the rigorously trained enthusiast for advanced empirical finance and, unlike the authors reviewed above, Singleton sees no need to work to gain readers' attention. His subject is the econometric treatment of asset-pricing models, and he both reviews the requisite econometric and statistical theory and describes the many financial market applications in some detail.

The highly compressed style takes for granted a good deal of prior knowledge of its subject matter. The reader wanting to learn estimation and inference theory would be best advised to study a dedicated text first, and use Singleton's chapters as the refresher that they are clearly intended to be.

Given these preliminaries, the reader's reward is a highly authoritative survey of a field of growing importance. Key issues are connections between modelling pricing decisions and econometric model formulation, and links between continuous time modelling and its empirical counterpart in high-frequency discrete data. The field is already too large to be covered completely in a single volume, but it is hard to imagine a more comprehensive and insightful treatment than this one.

Introductory Econometrics Using Monte Carlo Simulation with Microsoft Excel. First Edition

Author - Humberto Barreto and Frank M. Howland
Publisher - Cambridge University Press
Pages - 774
Price - £40.00
ISBN - 9780521843195

You've reached your article limit.

Register to continue

Registration is free and only takes a moment. Once registered you can read a total of 3 articles each month, plus:

  • Sign up for the editor's highlights
  • Receive World University Rankings news first
  • Get job alerts, shortlist jobs and save job searches
  • Participate in reader discussions and post comments
Register

Have your say

Log in or register to post comments

Most Commented

James Fryer illustration (27 July 2017)

It is not Luddism to be cautious about destroying an academic publishing industry that has served us well, says Marilyn Deegan

Jeffrey Beall, associate professor and librarian at the University of Colorado Denver

Creator of controversial predatory journals blacklist says some peers are failing to warn of dangers of disreputable publishers

Hand squeezing stress ball
Working 55 hours per week, the loss of research periods, slashed pensions, increased bureaucracy, tiny budgets and declining standards have finally forced Michael Edwards out
Kayaker and jet skiiers

Nazima Kadir’s social circle reveals a range of alternative careers for would-be scholars, and often with better rewards than academia

hole in ground

‘Drastic action’ required to fix multibillion-pound shortfall in Universities Superannuation Scheme, expert warns