2

I'm looking for a simple synonym that essentially means 'statistical measures'. Here's the context, sory if it's a little confusing. The real example is only more complex.

I'm using a classifications scheme like 0 through 5 = low, 6 through 10 = high. I'm applying that classification scheme to the minimum, mean, and maximum of sets of calculation results. In describing this, I'm wondering how to refer to those statistical measures? As in, what do you call a group of variables like minimum, mean, and maximum? "Statistical measures" or "statistical variables" might be the answer but is there any other simpler term for those entities as a group?


Example use where the minimums for all study sites happen to be classified as 'low' and the means all as 'high':

"Each case fits into the classification tier shared among all sets for each statistical measure."

What I'm trying to communicate is that for all test cases, if we're looking at the minimum all cases are classified as low, if we look at the mean all cases share the classification of high. This is worth saying, as it could've been that within the set of minimums for all test cases, some could've been classified in different ways, as low or high, but it worked out that all test cases share the same classification when looking within the same set of statistical...measures?

What is a clear and concise way to refer to these statistical measures?

  • 5
    A representative figure (an average such as the mean, median, mode, mid-mark; a measure of spread like the standard deviation ...) is simply called a statistic. This is a count-noun usage (plural 'statistics'), in contrast to the non-count noun statistics for the whole field of study. – Edwin Ashworth Mar 20 '17 at 15:14
  • 2
    If it fits with your context (i.e. each item of your statistical measures is important), you may refer to "key indicators". – Graffito Mar 20 '17 at 15:29
  • Those are helpful answers, thanks! Simply using 'statistic' could actually work well. If you change your comment into an answer I'll probably mark it accepted after a little longer. – cr0 Mar 20 '17 at 16:15
1

You would call what you are doing (statistical) data binning. According to Wikipedia (direct quote):

"Statistical data binning is a way to group a number of more or less continuous values into a smaller number of "bins". For example, if you have data about a group of people, you might want to arrange their ages into a smaller number of age intervals." 1

According to this page by the Department of Mathematics at the University of Texas (these are direct quotes from that page), there are also some other terms for data binning:

"Dividing a Continuous Variable into Categories"2

'This is also known by other names such as "discretizing," "chopping data," or "binning". Specific methods sometimes used include "median split" or "extreme third tails".' 2

I should also say that the page advises against this practice because you lose information (but that really is beyond the scope of your question and it can be useful for making histograms and is required for certain machine learning techniques).

According to the aforementioned Wikipedia page, the actual categories, in your case the low and the high, are referred to as bins.

Attribution

1 Wikipedia. (2018, February 28). Data binning. Retrieved March 23, 2018, from https://en.wikipedia.org/wiki/Data_binning

2 Smith, M. K. (n.d.). Dividing a Continuous Variable into Categories. Retrieved March 23, 2018, from https://www.ma.utexas.edu/users/mks/statmistakes/dividingcontinuousintocategories.html

  • That's what he's doing with the stats, but that isn't what he is asking about. He wants a hypernym for the things he is binning. – Phil Sweet Mar 23 '18 at 13:57
  • @PhilSweet thanks I'll add that (they are referred to as the bins). – JJ for Transparency and Monica Mar 23 '18 at 14:03

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.