Statistics notes Variables and parameters
BMJ 1999; 318 doi: https://doi.org/10.1136/bmj.318.7199.1667 (Published 19 June 1999) Cite this as: BMJ 1999;318:1667
All rapid responses
Rapid responses are electronic comments to the editor. They enable our users to debate issues raised in articles published on bmj.com. A rapid response is first posted online. If you need the URL (web address) of an individual response, simply click on the response headline and copy the URL from the browser window. A proportion of responses will, after editing, be published online and in the print journal as letters, which are indexed in PubMed. Rapid responses are not indexed in PubMed and they are not journal articles. The BMJ reserves the right to remove responses which are being wilfully misrepresented as published articles or when it is brought to our attention that a response spreads misinformation.
From March 2022, the word limit for rapid responses will be 600 words not including references and author details. We will no longer post responses that exceed this limit.
The word limit for letters selected from posted responses remains 300 words.
The Vancouver Group recommendation above says it all. Altman
and Bland have done us all a service by pointing out the
usage of the word 'parameter' in statistics.
It is of limited interest to readers of scientific journals
that changing fashions and the vagaries of folk etymology
dictate new illogical uses of existing words, entering
Merriam-Webster's and other dictionaries once sufficiently
prevalent in print.
Words used in medical journals should be as clearly and
unequivocally defined as possible. Nontechnical use of
technical terms serves only to confuse. Although most people
believe weight, force and pressure to be synonyms, when
writing for journals we should be allowed the use of
necessary distinctions.
Latin, English and other languages, have changed greatly
over the years. This is part of their charm, providing a
challenge to learners and job opportunities for
lexicographers. Ansell believes that Latin remained
"unchanged in context". If you can believe that, you can
b
Competing interests: No competing interests
The Vancouver Group recommendation above says it all. Altman
and Bland have done us all a service by pointing out the
usage of the word 'parameter' in statistics.
It is of limited interest to readers of scientific journals
that changing fashions and the vagaries of folk etymology
dictate new illogical uses of existing words, entering
Merriam-Webster's and other dictionaries once sufficiently
prevalent in print.
Words used in medical journals should be as clearly and
unequivocally defined as possible. Nontechnical use of
technical terms serves only to confuse. Although most people
believe weight, force and pressure to be synonyms, when
writing for journals we should be allowed the use of
necessary distinctions.
Latin, English and other languages have changed greatly
over the years. This is part of their charm. Ansell believes
that Latin remained "unchanged in context". If you can
believe that, you can believe anything.
Competing interests: No competing interests
Sir,
Altman and Bland provide another clear exposition of statistical
terminology. However, their comment that the term parameter is misused in
the phrase "within certain parameters" ignores their own previous
paragraph, where they state that "parameters are values that can be
altered to see what happens to the performance of some system."
Parameter would be correctly used in the phrase "within certain
parameters" if the truth of the statement was conditional on the values of
the parameters. Estimates of these unknown parameters will necessarily be
based on sampled data, and will vary from sample to sample depending on
the value of the variables.
In this sense there is a confusion between the sampled estimate of a
parameter based on variables and its true unknown value. It is analogous
to the elementary mistaken interpretation of the p-value as being the
probability of the parameter lying within the confidence interval, rather
than the confidence interval covering the area the parameter is in.
Evan Roberts
Competing interests: No competing interests
Sir,
The English language is alive, with thousands of new words created every
year in addition to new meanings to existing words.
The Webster English dictionary additionally defines parameter to mean :-
1. an independent variable used to express the co-ordinates of a variable
point and functions of them
2. any of a set of physical properties whose values determine the
characteristics or behaviour of something <parameters of the atmosphere
such as temperature, pressure, and density>
3. a characteristic element e.g. political dissent as a parameter of
modern life
4. a limit or boundary
These are not misuses of the word. Professor Altman and statisticians do
not hold sole licence to the English language. Many English words have
more than one accepted meaning. If you want language to remain unchanged
in context, use a dead language like Latin.
Competing interests: No competing interests
use of the word 'parameter'
I find it a good article and the authors are actually helping us out
by reviewing important concepts often taken for granted and misused. Altman
et al. should have also touched on the word 'statistic' as to samples to
help make the explanation complete re statistic versus parameter. Yet,
this is an excellent article and a good read.
Competing interests:
None declared
Competing interests: No competing interests