Arnold's "Signature"

Anonymity is part of the culture when it comes to refereeing papers submitted for possible publication in economics, econometrics, and statistics. Referees' names are typically "blinded", and some journals use a "double-blind" process, so that authors names are not know by the referees. Not all disciplines use this approach.

The double-blind approach is far from perfect, especially given how easy it often is to identify authors  by locating a "working paper" version of their article through an internet search. In addition, referees often effectively "reveal" their identity by insisting that authors include references to the referee's own work.

Sometimes, though, referees expose themselves quite unwittingly. Here's a case in point. 

The late Arnold Zellner was a giant among econometricians and statisticians alike. He gave us the SUR estimator, 3SLS, and he was the founding father of Bayesian econometrics. His many contributions to the statistics profession culminated in a stint as President of the American Statistical Association.

I've mentioned previously (here and here) that Arnold was immensely helpful to me when I was getting started on my Ph.D. in the early 1970's. He was later one of my external examiners, and we had quite a lot of contact after that - for example when I was an Associate Editor of Journal of Econometrics for nearly a decade, and Arnold was one of the Co-Editors.

I also came to be aware when Arnold was a referee for my own papers. He "signed" the reports.

Back in the olden days when secretaries typed letters using a typewriter, a font was a font was a font.  You couldn't slip back and forth between (say) Courier font and mathematical symbols. The advent of the IBM Selectric typewriter (1961 to 1986) revolutionized the typing of scientific manuscripts:

The key innovation was the "golf ball". Different golf balls were available for different fonts, and the typist could change from one ball to another by lifting the black lock-tab :

Of course, changing the golf ball became somewhat disruptive if, for example, you wanted use different fonts in the one line (sentence,........) of typing. Imagine moving from courier to script, to mathematical symbols, and back to courier. That's four physical changes of the golf balls. Needless to say, some typists continued with some of the short-cuts that they had developed in pre-golf ball days!

One such person was Arnold's secretary for many years. She must have typed hundreds of referee reports for him. Now, think about a typical referee's report. It might begin with a short summary of the key contributions that the paper makes; followed by a list of major comments, criticisms, and suggestions. It generally ends with a list of some minor points dealing with clarifications that are needed; grammatical or typing errors; etc.

Usually, the latter list will begin with a page and line reference - maybe something like the following:

"1. p.5, line 15: Explain this in more detail......"

Just as "page" is abbreviated to "p.", the word "line" is often abbreviated to "l.", and it used to be traditional to type (or write(!)) the latter symbol in a script font, if possible:

                                                                 

Arnold's secretary had the interesting habit of typing a left parenthesis, "("; then back-spacing and over-striking it with a forward slash, " / ".The end result was a close approximation to a script "ell".

    

Whenever I saw this, I knew who had dictated the letter and who had typed it.

This went on for years! I remember finally mentioning it to Arnold around 1992 - about 20 years after we had first started corresponding. It came as a revelation to him, and I can still recall the look on his face as the implications sunk in!

© 2014, David E. Giles