Home > Statistics Every Writer Should Know > The Stats Board > Discusssion
Variance and Standard Deviation
Message posted by Jorge on November 30, 1999 at 12:00 AM (ET)
This might be in part a tecnichal question:
I am developing a research project, and one of my goals is to compare wether is there a diference between the hospital days post surgery of two different population of patients. I have all my database in an excel worksheet, and I tried to run a non paired two tailed T test. The question is Shoul I treat this as i had two samples with equal or unequal variance?, since this is actually the next question excel asks me when I try to run the T test. Besides and may be more importan I don't understant what does variance means on this context. That is question Number 1.
Question Number two is regarding the standard deviations of this two populations:
Pop #1: mean 4.14 SD 3.85
Pop #2: mean 7.52 SD 13.13
I do not understant how can the standar deviation be bigger that the mean?
Thank you for your time, by the way I think this page is great.
Cheers.
Jorge
READERS RESPOND:
(In chronological order. Most recent at the bottom.)
Re: Variance and Standard Deviation
Message posted by JG on November 30, 1999 at 12:00 AM (ET)
The variance is the square of the standard deviation. The standard deviation can be much bigger than the mean. Let us assume you have ten observations of 1 and one observation of 56, then the mean is 6 and the standard devition is 15.81 . The sample standard deviation would be 16.58 in this case.
Re: Variance and Standard Deviation
Message posted by Vern Myers on November 30, 1999 at 12:00 AM (ET)
Your standard deviations are 3.85 and 13.13, so your variances are 14.82 and 172.4; therefore, you use the two-sample t-test assuming unequal variances.
Your $5 contribution helps cover part the $500 annual cost of keeping this site online.