Some funny things happened on the way to the limit of error standard Page: 3 of 10
This article is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided to Digital Library by the UNT Libraries Government Documents Department.
The following text was automatically extracted from the image on this page using optical character recognition software:
other fellows (both Ms. and Mr.) were doing either.
Now, however, well headed into the 1970s, some glimmers
of improvement are discernable. The jargon of the early days of
nuclear material management is being scrutinized, shaken down,
and made consistent with concepts and procedures used elsewhere.
"Limit of error" is one such jargonal element, and it is the one
upon which I will concentrate in this discussion.
Following that flurry of puzzlement a decade ago and
some disappointment at not being able to resolve the differences
and considerable frustration at being told "you'll never get it
straightened out" by some of the pioneers in the game, several
years of no contact passed. Then, in September, 1970, I was
asked to become a member of "Subcommittee N15-3 (Statistics) of
the American National Standards Institute Stardards Committee
N15 (Methods of Nuclear Materials Control)." In common with
many literary characters of the 19th century, little did I know
what was in store for me. The first few months of Subcommittee
activity, especially in the development of ANSI Standard N15.5
on Statistical Terminology and Notation for Nuclear Materials
Management, renewed my interest in helping to bring statistical
methods to the needs of nuclear materials managers. Moreover,
I gradually became aware that committees such as ours really
could bring about needed adjustments. Along with the ability
to adjust comes the responsibility to promote those adjustments.
And that is the spirit in which these remarks are offered.
II. "Limit of Error" in Statistical Textbook Literature.
Prompted by those early requests for assistance, I ex-
amined a number of basic mathematical and statistical texts to
try to determine the background of "limit of error." qly primary
recollection is that I came up empty-handed. There the matter
lay for several years.
As I considered this presentation, I decided to retrace
my search. I examined a large number (but by no means a random
sample) of both old and new books. Neither James and James'
Mathematics Dictionary (D. Van Nostrand Company, Inc., 1959) nor
Kendall and Buckland's A Dictionary of Statistical Terms (Hafner
Publishing Company, Inc., 1971) mention "limit of error." Only
three of the many books selected use the phrase in their indexes,
and none of those really develop and continue to use the concept.
From Cochran and Cox's Experimental Designs (John Wiley
and Sons, Inc., 1957, p. 27):
"2.22. Number of Replications for Prescribed Limits of
Error. The confidence limits for 6, the true difference between
the effects of two treatments, are
6 = d t st
Here’s what’s next.
This article can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Article.
Moore, R.H. Some funny things happened on the way to the limit of error standard, article, January 1, 1974; New Mexico. (https://digital.library.unt.edu/ark:/67531/metadc1017124/m1/3/: accessed April 21, 2019), University of North Texas Libraries, Digital Library, https://digital.library.unt.edu; crediting UNT Libraries Government Documents Department.