Hi Carol
On page 124, (I.3.121) the denominators are incorrect. Inside the chi square inverse, left should be (1+alpha)/2 and right should be (1alpha)/2.
Joy
Errata
Forum rules
DISCLAIMER: We do not warrant or represent that this forum or its content is free of viruses, worms or other code that might be contaminating or destructive. We cannot guarantee that documents or files downloaded from the Site will be free from viruses and we do not accept any responsibility for any damage or loss caused by any virus. Accordingly, for your own protection, you must use viruschecking software when using the forum. You must not post or provide to us via the forum, any document or file which you believe may contain a virus. You must virus check any document or file which you intend to post or provide to us via the forum. You must ensure that any document or file you intend to post to the forum does not contravene any applicable laws or contravene any person's legal rights. We do not accept any responsibility for any damage or loss you may suffer.
DISCLAIMER: We do not warrant or represent that this forum or its content is free of viruses, worms or other code that might be contaminating or destructive. We cannot guarantee that documents or files downloaded from the Site will be free from viruses and we do not accept any responsibility for any damage or loss caused by any virus. Accordingly, for your own protection, you must use viruschecking software when using the forum. You must not post or provide to us via the forum, any document or file which you believe may contain a virus. You must virus check any document or file which you intend to post or provide to us via the forum. You must ensure that any document or file you intend to post to the forum does not contravene any applicable laws or contravene any person's legal rights. We do not accept any responsibility for any damage or loss you may suffer.

 Posts: 9
 Joined: Thu Apr 11, 2013 7:06 am
Re: Errata
How about an estimate of the simple returns for each asset given by:
r_simple_asset_i = r_log_asset_i + 1/2 Variance_asset_i
I saw a proof that the variance of the log returns and the variance of the simple returns are approximately equal in some paper I read a while back. Then from the above, the expected return on the portfolio is a weighted sum of the constituent simple returns and the variance of the portfolio is given by the matrix formula found in the book. Finally, the expected log return on the resultant portfolio is approximated by:
r_log_portf = r_simple_portf  1/2 Variance_Portf
This is just an approximation, but it works pretty well when I've tried it. The errors are slim, and given the noisy nature of the inputs, is probably irrelevant in comparison to the noise.
Cheers
Walter Zelhofer Jr.
coalexander wrote:
> Dear Panos,
>
> Many thanks for your comments  it is very beneficial to me when readers
> point out the typos.
>
> The Hessian on p30 has element f_13 eqaul to d^2L/dlambda dx and since L =
> ....[b:25qd4suh]minus[/b:25qd4suh]lambda(x + y + 4) I think f_13 is equal
> to 1. And similarly for f_13.
>
> I write all vectors as column vectors, and on page 56 the line above
> (I.2.22) has already been corrected from the first printing, where the
> traspose for [b:25qd4suh]w[/b:25qd4suh] was omitted (and also, the first
> element came out as w_t not w_1, these errors being introduced by type
> setters). For readers with the first or second printing, which seems to
> include you, there is a list of errata on the page for Vol I on my
> website.
>
> I agree that in the next edition I should add more to Section I.1.4.8 to
> address the difficulties encountered when trying to express the log return
> on a linear portfolio in terms of log returns on the assets, and I welcome
> your comment in this respect.
>
> I hope you find the reading of Vol I worthwhile, and look forward to your
> future participation in the discussion forum.
>
> Best Wishes, Carol
r_simple_asset_i = r_log_asset_i + 1/2 Variance_asset_i
I saw a proof that the variance of the log returns and the variance of the simple returns are approximately equal in some paper I read a while back. Then from the above, the expected return on the portfolio is a weighted sum of the constituent simple returns and the variance of the portfolio is given by the matrix formula found in the book. Finally, the expected log return on the resultant portfolio is approximated by:
r_log_portf = r_simple_portf  1/2 Variance_Portf
This is just an approximation, but it works pretty well when I've tried it. The errors are slim, and given the noisy nature of the inputs, is probably irrelevant in comparison to the noise.
Cheers
Walter Zelhofer Jr.
coalexander wrote:
> Dear Panos,
>
> Many thanks for your comments  it is very beneficial to me when readers
> point out the typos.
>
> The Hessian on p30 has element f_13 eqaul to d^2L/dlambda dx and since L =
> ....[b:25qd4suh]minus[/b:25qd4suh]lambda(x + y + 4) I think f_13 is equal
> to 1. And similarly for f_13.
>
> I write all vectors as column vectors, and on page 56 the line above
> (I.2.22) has already been corrected from the first printing, where the
> traspose for [b:25qd4suh]w[/b:25qd4suh] was omitted (and also, the first
> element came out as w_t not w_1, these errors being introduced by type
> setters). For readers with the first or second printing, which seems to
> include you, there is a list of errata on the page for Vol I on my
> website.
>
> I agree that in the next edition I should add more to Section I.1.4.8 to
> address the difficulties encountered when trying to express the log return
> on a linear portfolio in terms of log returns on the assets, and I welcome
> your comment in this respect.
>
> I hope you find the reading of Vol I worthwhile, and look forward to your
> future participation in the discussion forum.
>
> Best Wishes, Carol

 Posts: 9
 Joined: Thu Apr 11, 2013 7:06 am
Re: Errata
Page 170 where you estimate the prediction interval for the Billiton Limited regression:
Your estimate of V(y0yhatX1 = 0.1, x2 = 0.2) is .00155.
When I checked it using the following functions in excel: =MMULT(MMULT(Covar_Matrix_Range,TRANSPOSE(Vector_Range)),(Vector_Range))+MSResidual
Where Covar_Matrix_Range is the range for the covariance matrix of the coefficient estimates, and the Vector_Range is the vector of {1,0.1,0.2},
I get .00143356
Did I miss something, or is there an error?
Your estimate of V(y0yhatX1 = 0.1, x2 = 0.2) is .00155.
When I checked it using the following functions in excel: =MMULT(MMULT(Covar_Matrix_Range,TRANSPOSE(Vector_Range)),(Vector_Range))+MSResidual
Where Covar_Matrix_Range is the range for the covariance matrix of the coefficient estimates, and the Vector_Range is the vector of {1,0.1,0.2},
I get .00143356
Did I miss something, or is there an error?
Who is online
Users browsing this forum: No registered users and 1 guest