Thanks for all the helpful suggestions... Cheers, CCC
"Art Kendall" <[EMAIL PROTECTED]> wrote in message [EMAIL PROTECTED]">news:[EMAIL PROTECTED]... > try doing a scattergram of your two variables. It should look much more like a > cloud than a line. > > "Anon." wrote: > > > Chia C Chong wrote: > > > > > > I have 2 random variables (X and Y). The covariance,c was found equal to > > > 20.2006 and their correlation coefficient,p was 0.0245. > > > > > > From the statistical book, if their c=0, means that X and Y are uncorrelated > > > i.e p=0. However, in my case, c is quite large but p is extremely > > > small...So, what justification could I said with this kind of data?? > > > > > It measn the variances are large. If s_A is the standard deviation of > > A, then > > > > p_XY = c_XY/(s_X*s_Y) > > > > So for your data, s_X*s_Y = 824.5. This is why we use p, it's re-scaled > > so that the variances are 1, so we can compare correlations of variables > > with different variances. In this case, p looks very close to 0. > > > > Bob > > > > -- > > Bob O'Hara > > Metapopulation Research Group > > Division of Population Biology > > Department of Ecology and Systematics > > PO Box 17 (Arkadiankatu 7) > > FIN-00014 University of Helsinki > > Finland > > > > tel: +358 9 191 28779 mobile: +358 50 599 0540 > > (Yes, I have finally joined 21st Century Finland) > > fax: +358 9 191 28701 email: [EMAIL PROTECTED] > > To induce catatonia, visit <http://www.helsinki.fi/science/metapop/> > > > > It is being said of a certain poet, that though he tortures the English > > language, he has still never yet succeeded in forcing it to reveal his > > meaning > > - Beachcomber > ================================================================= Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =================================================================
