Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 2 down vote favorite

In my research I'm comparing the variance of a method and I would like to describe the overall variance between individuals and the variance of the replicates of these individuals.

Things like 'comparing the intra-individual variance and between-individual variance' seems to get people confused. I would like to make a short brief notice of this without having to go to much in details about the experiment.

What would be a way of describing this setting more clearly but still within if possible one sentence?

To clarify: I have 10.000 measurements for 60 individuals. For each measurement I could calculate for example the standard deviation as a method of variance. I also have 5 replicate measurements per individual. I could calculate the standard deviation for each of the 10.000 measurement in the replicates. So now I have the variance of the measurement when looking in a population AND I have the variance when looking at replicates. When you would now have to describe these 2 types of variance in a single sentence how would you do that without going into to much details?

share|improve this question
Hello Sander. I'm sorry but I don't really understand what you're exactly asking, I'm voting to close it as not a real question. You can edit the question (even when already closed) and if it gets within the standards, it will be voted to be reopened. – Alenanno Jul 21 '11 at 10:41
Sorry to hear that Alennano, in what way should I try to make myself more clear? I was hoping that within the English language there would be a better way to define variance within an entity and between entities without having to use to much details. – Sander Jul 21 '11 at 10:57
I'm not sure, you could try schematising your question. But let's see if others agree with me or not, maybe it's just me. :) – Alenanno Jul 21 '11 at 11:14
1  
I think this question is interesting, but upon further scrutiny, it probably should be on Writers.SE, since what you are asking for is more like a critique than a vocabulary question. I've voted to migrate it. – Kit Jul 21 '11 at 12:15
2  
@Kit: Writers? what would they know about statistics? (or here for that matter). This is a question about technical localized vocabulary. It is a great question for statistics.SE (where they 'own' such terminology) – Mitch Jul 21 '11 at 13:49
show 2 more comments

migrated from english.stackexchange.com Jul 24 '11 at 17:42

2 Answers

up vote 1 down vote

As I understand the question, it is a matter of comparing the variance of an individual across multiple repeated instances and the variance of one instance across multiple individuals. If so, then I think the terms group variance and individual variance succinctly express the desired meanings.

share|improve this answer
up vote 0 down vote

In addition to @rubergly's excellent suggestions, which are commonly seen in research fields, you might consider within-subjects variance and between-subjects variance. This terminology was common when I worked in experimental psychology, but may have fallen out of favor with the push to turn human 'subjects' into 'participants.' Of course, if you are talking about non-human subjects, then it would still be very appropriate.

share|improve this answer
While I don't doubt that between-subjects variance is commonly used, I suspect that among-subjects variance is preferred for groups larger than 2. However, this does sound a little unwieldy, so I'm wondering if the normal between/among rule applies here. – rubergly Jul 21 '11 at 21:37
1  
@rubergly I agree that among-subjects would be more grammatically proper, but I have never heard it in an experimental science context. I've only ever heard/used between-subjects. – Kit Jul 21 '11 at 23:08

Your Answer

 
discard

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.