i know what correlation is haha id be in real trouble if i didnt right now. what i mean is, they didnt provide us with correlation, so sohuld we always assume its 1?
also is there any way to calculation mean, stddev, and covariance if youre given expectational data
I’m not sure what you’re asking. So here is another question. Do the same for these data sets. r is different for each data set. It is calculated by the calculator. Year Return of Hedge Fund 1 Return of Hedge Fund 2 1998 1 0.30 2 0.80 1999 1 -0.40 2 -0.50 2000 1 -0.30 2 -0.05 2001 1 0.00 2 0.00 2002 1 -0.10 2 -0.65 2003 1 0.20 2 0.70 Result: r = 0.82 Covariance = 0.113
With expectational data this won’t work. Have to do it the long way.
turbo, does the calculator formula work if you have more than 2 variables? i assume not because theres only x and y.
thanks for the example. i did get .82 for r, but im not getting 0.113 for covariance. (sx)(sy)® = .27386 x .5983 x .82 = .1349 is your rounding very different from mine? or am i doing something wrong? maybe its my calculator?
I get 0.135 also
the show NY: That is a good question. I get the same answer as you. This was taken from QBank Question ID#: 29248. In their answer when they calculate the Covariance they divide it by 6 and not 5 (n-1). They appear to be using the population std deviations, and not the sample std deviations? Maybe someone can help here? Here is the narative: “An analyst is examining the relationship between the returns of two hedge funds, Hedge Fund 1 and Hedge Fund 2. Hedge Fund 1 was started in 1995 and Hedge Fund 2 was started in late 1997. The returns for both funds for the six full years between 1998 and 2003 are listed below.” Maybe they are saying our data is the full population so we need to use population variances? But Hedge fund 1 is not the full population (missing years 1995-1997). Hopefully someone with QBank can attempt the question and respond back.
I think you answered your own question. All the data is there, so it would not make sense to use sample std dev. So you use the population std dev and arrive at .11193. Agree?
There is additional information to the problem…after the table it gives you the variance of returns for HF1 @ .0625 and HF2 @ .2983. take the sqrt of those and multiply it with the r to get the covariance. its one of those “tricky” problems where they actually do the work for you - you just have to know where to look.
I can agree with that. Probably not worth worrying about. If it comes up on the exam it’s only one mark and we can get a pretty good guess anyways.
thanks for all your help turbo. very nice of you to post that example.
the show NY Wrote: ------------------------------------------------------- > thanks for all your help turbo. very nice of you > to post that example. I’ve been lurking on here for ages without posting a thing. If I can pay it forward just once, maybe some karma will come my way during the exam 
I got the same. Great thread! This way can save at least 3 minutes plus accuracy. Thanks a a lot for the input TurboNerd! the show NY Wrote: ------------------------------------------------------- > thanks for the example. i did get .82 for r, but > im not getting 0.113 for covariance. > > (sx)(sy)® = .27386 x .5983 x .82 = .1349 > > > is your rounding very different from mine? or am > i doing something wrong? maybe its my calculator?