Register to reply

Sample and population variances: elementary question

by nomadreid
Tags: elementary, population, sample, variances
Share this thread:
nomadreid
#1
Jan31-13, 01:15 AM
P: 562
Given a sample of a normally distributed population, then the sample variance ≈the population variance divided by the sample size. Nice. However, if one now increases the sample size to the population, this becomes that the population variance ≈ the population variance divided by the population size, which is absurd. What elementary concept am I missing here? Thanks in advance
Phys.Org News Partner Science news on Phys.org
Mysterious source of ozone-depleting chemical baffles NASA
Water leads to chemical that gunks up biofuels production
How lizards regenerate their tails: Researchers discover genetic 'recipe'
Simon Bridge
#2
Jan31-13, 01:38 AM
Homework
Sci Advisor
HW Helper
Thanks
Simon Bridge's Avatar
P: 12,764
The idea is to estimate the population variance from a sample.
http://en.wikipedia.org/wiki/Varianc...ample_variance
ImaLooser
#3
Jan31-13, 01:58 AM
P: 570
Quote Quote by nomadreid View Post
Given a sample of a normally distributed population, then the sample variance ≈the population variance divided by the sample size. Nice. However, if one now increases the sample size to the population, this becomes that the population variance ≈ the population variance divided by the population size, which is absurd. What elementary concept am I missing here? Thanks in advance
In statistics the idea is that you have a population and are trying to figure out its parameters. So you take a sample to get an estimate.

The population parameters are assumed to be constants. The sample parameters are random variables, because they will vary from sample to sample.

You are also confusing the sample variance with the variance of the sample mean.

The variance of the sample mean (usually) converges to zero, while of course the population variance does not. The sample variance converges to the population variance.

This stuff is confusing, but it is important to get it straight or you will never understand statistics. So good for you for asking.

nomadreid
#4
Jan31-13, 02:48 AM
P: 562
Sample and population variances: elementary question

From ImaLooser
You are also confusing the sample variance with the variance of the sample mean.
You hit the nail on the head! Perfect. I now understand. Thanks very much, ImaLooser.
.
And thanks also to Simon Bridge for replying.
ssd
#5
Feb15-13, 06:11 AM
P: 240
Sample variance is NOT equal to population variance divided by sample size.
nomadreid
#6
Feb15-13, 07:55 AM
P: 562
ssd:
Sample variance is NOT equal to population variance divided by sample size.
Yes, I know, that was the absurdity in my mini-proof that something was wrong with the original assumptions. That is, if I make a point that X is wrong because it leads to 1=0, then saying that 1≠0 is missing the point.


Register to reply

Related Discussions
Calculating Variances of Functions of Sample Mean Calculus & Beyond Homework 1
Sample variances & ANOVA: How different is too different? Set Theory, Logic, Probability, Statistics 3
Consider a random sample n from a population Set Theory, Logic, Probability, Statistics 3
10.7 Small-Sample Inferences Concerning A Population Mean Calculus & Beyond Homework 0
Question about vaiance, population and sample Set Theory, Logic, Probability, Statistics 12