covariance of 2 return data

So I know how to do the covariance of 2 return data when each return is given a probability, but I haven’t seen an example when the returns are for sure like in a yearly return… year … asset a … asset b 1 …10%…12% 2 … 8%…-2% 3 …3% … 5% can someone show my the calcs for this? Thanks!

(Ra - MUa)(Rb - MUb) for years 1, 2 and 3. divide by n-1 = 3-1 = 2 since this is a sample Ra is 10, 8, 3 the returns. Rb is asset b returns MUa is average of a, MUb is average of b

Use BAII 2nd data - load it in 2nd stat - should have all the basics you need for cov. just be careful re: pop or sample. There are threads on this going back 2 years or so. Should be around.

june2009 Wrote: ------------------------------------------------------- > Use BAII > > 2nd data - load it in > 2nd stat - should have all the basics you need for > cov. > > just be careful re: pop or sample. There are > threads on this going back 2 years or so. Should > be around. so what’s the symbol for covariance on the calc? because all I need is the average to get the covariance and it would be faster to just calculate the average instead off all that…

just did a quick search as recomended… well using 2nd data, and 2nd stat I can calculate std dev of A, std dev ov B, and correlation coefficient within 30 seconds. Given all that, you can compute covariance in another 20 sec with corr = covAB / sigA * sigB then just solve for Cov

so what’s the symbol for correlation in the calculator?

i think “p” is correlation

Where can we find the “p” symbol? Have spent the last 10 minutes trying to flipping find it.

Just download the manual for Texas BA II Plus. It shows you the steps. You have to put the calculator in linear regression mode. Then enter your data, and the calculator gives you the correlation coefficient (this is the “r” value under the “STAT” sheet). Once you have “r” you can plug-n-chug the covariance formula (see jun2009’s post above).

Did anyone do it on their calculator? Do you get covariance as 6.99? (Correlation .277?)

I can confirm that the correlation is 0.277 on my calculator. However, I think someone (with a lot of extra time) needs to do it the manual way and confirm the answer. The original post is almost a year old, so I don’t think the OP is going to confirm what the answer is.

Well then, I guess it should be correct. I use HP12C. It is highly unlikely we both made the same error on different calculators!