Re: [Gretl-devel] State Space Modeling: possible mistake in User's Guide

Em 6 de março de 2018, Jack escreveu: On Tue, 6 Mar 2018, Henrique Andrade wrote: > > Dear Allin and Jack, >> >> I think there is a little mistake in chapter 33 of the Gretl's User Guide. >> It states that x_t is a (k x 1) matrix on page 273 (the definition is >> located in the texte under the equation 33.2) and that x_t is a (T x k) >> matrix on page 274. >> > Uhm, maybe I don't get you point, but on page 274 we don't claim that x_t > is a Txk matrix. We say that x is, and x_t is understood to be the > transpose of the t-th row of x. > > Or have I misunderstood your remark? Dear Jack, I've got your point when you said "on page 274 we don't claim that x_t is a Txk matrix ". But I think the guide is a little bit confusing. User' guide says x_t is a (k x 1) vector (last line of the page 273). After that, on the next page, a "table" states that the symbol x has the dimension (T x k). This confused me :( Once we need to calculate A'_t times x_t (equation 33.2) and, as stated in the "table", A_t is a matrix with dimensions (k x n), the order of x_t should be (k x 1). This is clear for me. But when "table" says the dimension of x is (T x k) I imediatelly think x is the Hansl's representation for x_t in equation 33.2. Finally, I would like to thank you for your attention and also I would like to say I'm not an expert in that subject ;-)