Take the 2-minute tour ×
English Language & Usage Stack Exchange is a question and answer site for linguists, etymologists, and serious English language enthusiasts. It's 100% free, no registration required.

I am trying to choose a title. I have a big data set and I will get subsets of this data set using statistical techniques (random sampling etc.).

Which one of the following is correct? If more than one is suitable, is there a nuance between them?

  • create subset data sets
  • construct subset data sets
  • get new subset data set

I am not a native speaker; therefore if all of them are wrong, I am open to suggestions.

share|improve this question
A subset is still a set, and if it was created from a data set, it's still a data set. So I wouldn't bother with the word(s) "dataset" at all. I think "create" is better than "construct", and "get new subset" sounds like an inline comment to program code, not really suitable for general-purpose writing. –  FumbleFingers Dec 20 '11 at 17:32
I thought I'd seen a verb form of the word "subset", as in "we subset the data", but I can't find a reference to it, so I'm not posting it as an answer. –  Mr. Shiny and New 安宇 Dec 20 '11 at 18:24
You are getting good answers here, but if this is writing intended for an audience of statisticians it may also be wise to consult stats.stackexchange.com, since they will be well-versed in the most common usage patterns for their field. –  Jonathan Van Matre Dec 20 '11 at 19:30

7 Answers 7

up vote 5 down vote accepted

I would write for example

Using random sampling, we obtain these data subsets.

The verbs create, construct and get are alright but sound awkward.

Create suggests that something is produced from scratch, construct suggests that an elaborate procedure exists to produce something, and obtain suggests that something is produced from something else.

share|improve this answer
Actually : there exists data pre-processing steps. But I do not consider them to be too elaborate. –  Atilla Ozgur Dec 20 '11 at 17:41

All of them are correct, except that get a new... seems more natural than get new.... Also note that assemblies derived via random sampling are often referred to as drawn rather than created (e.g.: "Eight sets/subsets/datasets/samples were drawn from the population") to underpin the notion they are random rather than deterministically constructed.

share|improve this answer
Since drawn is not a verb, can I use "draw subsets from data". –  Atilla Ozgur Dec 20 '11 at 17:36
Yes; for example, "We drew eight subsets from the population", "We randomly selected eight subsets from the population", "We randomly constructed eight subsets from a thousand random members of the population", "We draw random subsets in the following way: ...", etc. Exact wording must vary to accord with circumstances. –  jwpat7 Dec 20 '11 at 17:43
Point of clarification: "were drawn" is a verb. But jwpat is correct. –  Jonathan Van Matre Dec 20 '11 at 19:26

Maybe 'extract' captures the fact that you're processing the original data to obtain the subsets e.g. "Using random sampling, we extracted the following subsets...".

share|improve this answer
Are you using extract as "To take by selection" –  Atilla Ozgur Dec 20 '11 at 17:44
Yep, pretty much, although it could be thought of as more informal as in "extracting the juice from an orange" –  tinyd Dec 20 '11 at 17:47

I would use extract, meaning "to draw forth".

Also, saying "subset data sets" is redundant. The word "subsets" already includes "sets", and basically means "a smaller set from a larger set." So, I would describe what you are extracting as data subsets, as in the following examples:

Given the original data, we extracted various subsets based on the following criteria...

We extracted these data subsets from the original study...

We used random sampling to extract a subset of data...

share|improve this answer

By far the most common term I have come across that is used to convey this meaning is 'extract'. I would suggest it on the strength of its familiarity, precedence and also for being very unambiguous.

There could be a better term, though, I am not sure.

share|improve this answer

Are you sure you mean title? Because it seems you talk about an abstract. A title would sound like "Creation of a subset...".
Indeed, extract is commonly used in sampling, and you can also simply say we sample a subset or we take/draw a sample
Get is informal and is not preferable in formal literature.
Construct has a nuance of elaboration, often as a result of an algorithm or procedure in which all steps are given.
Obtain is very common and has a formal touch.

share|improve this answer

You could use the phrase "collect a subset from the dataset."

Another prviously mentioned answer "extract subsets" would be appropriate.

If you're looking for a title: "Extracting Subsets: Various Statistical Techniques" would probably be appropriate for your assignment.

A subset is a portion of a set, and if you're collecting it from a dataset, then the term data set subset is incredibly redundant.

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

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