EViews.com

yes, this seems to work! problem resolved. thank you.

ok, but i need the current value to be stuffed into a temporary variable !current_id_value ... let's say my identifier variable is called myid myid(xxx) does not do the job since the reference inside the brackets is relative to the whole range, not the current sample, otherwise it would be straightf...

!i would just return the current level of the counter !i (e.g. 1 through 500)
but my id values are non-sequential and do not start at 1, e.g. 1001, 1005, 1016...
these are the ones i'd like to retrieve

thanks, your continuous support is highly appreciated. it works provided you have no sample restriction before running these lines (i.e. had to do "smpl @all" before) now, inside my loop for !i=1 to !ncross smpl if @crossid = !i 'do something here next how can i obtain the current id value...

this yields an error: "@crossid is an illegal or reserved name in !ncross=@max(@crossid)"

i worked out the following solution, maybe someone can confirm that is correct: look up critical value of t-distribution by @qtdist(1-(alpha/2),n-1) where alpha would be the significance level (e.g. 0.05). The second argument would be the degrees of freedom, which seem to be defined as the number of...

Hi,
the VEC output includes standard errors in () and t-statistics in [], but neither p-values nor critical benchmark values. how can one determine the one or the other so as be able to tell if a coefficient is signficant?
Thanks,
Steve

i have the same question too.
can anybody shed light on this issue, i.e. how to determine whether for example the coefficients to the cointegration equation are significant?

ok, and how would i get the maximum? i tried max(@crossid) but with no luck

besides, the matrix that coint returns includes the test statistics, but not the critical values or p-values in order to decide about reject of the null or not! where is one supposed to obtain the critical values (if not from the table)?

oh i wasn't thinking about text, i just need values not returned by the matrix, e.g. the p-value of the test for cointegrating restrictions. the issue when using a table is that the content won't always be at the same place, i.e. the row coordinate of the cell you're looking at may vary in function ...

so i have to think of it as a pointer that magically moves on to the next unique id value after being used? I looked it up in the docs but they aren't very precise: "@crossid observations in range, returns the cross-section identifier index." but how would i know the number of unique id va...

Hi, I'm using the "coint" method for co-integration of the var object and were disappointed to see that the matrix which is supposed to store the results for further processing is very incomplete. for example, if you include a test of cointegrating restrictions (which you do by imposing co...

i'm also having the problem that the coint function does not have the option to return a matrix with all the results that normally show up in the output tables.
has anybody a solution to that?
can you somehow "grab" the relevant information from the output tables?

thanks for joining my thread, but can you elaborate more how i make @crossid work for me in iterating over all unique identifier values?
i understood @crossid such that it just stands for whatever the variable name of my dataset is.