Thanks a lot for your answer. It is now perfectly clear!
Best,
Pierre
Christian Beckmann a écrit :
> Hi
>
> yes, that's why I used brackets to point to the fact that these are done
> in sequentially (though I messed up the order ;)
>
> In melodic - as reported on the command line - the mean image is removed
> first. From this, the mean time series is then removed.
> cheers
> christian
>
>
> On 10 Jun 2007, at 20:44, Pierre Lafaye de Micheaux wrote:
>
> Dear Christian,
>
> Your answer is much more precise. Thank you.
>
> But i have a question about this formula:
> X' = X- t_mean * ones(1,V) - ones (T,1) * v_mean
>
> If i use this formula, the matrix X' is neither centered for the rows,
> neither centered for the columns.
>
> Maybe i should first center the matrix for the rows to obtain a matrix X'
> and then center this matrix X' for the columns to obtain a matrix X'' ?
> Or the inverse ? That is:
> first center the matrix for the columns to obtain a matrix X' and then
> center this matrix X' for the rows to obtain a matrix X''
>
> What do you think about this point?
>
> Best regards,
>
>
> _
> €
>
--
Pierre Lafaye de Micheaux
Bureau 210, bâtiment BSHM
1251 avenue centrale BP 47
38040 GRENOBLE Cedex 09
FRANCE
Tél.: 04.76.82.58.73 / Fax: 04.76.82.56.65
[log in to unmask]
http://www.biostatisticien.eu
|