Re: Ordered probit model
Posted: Thu Apr 26, 2012 2:42 pm
Here's an example that replicates the computation. Note that the Makepcomp default is to use the correlation (the docs are wrong on this one -- I'll get them corrected) so that we have to scale the Y before use. At the end of this, the series in A1, A2, A3, matches the matrix of scores in SCORES. I just grabbed the series LBLA, etc. for this example; you should substitute your own.
As noted in the manual
group group01 lbla loan oil orders
group01.makepcomp(eigvec=evec) a1 a2 a3
group group02 a1 a2 a3
group group03 (lbla-@mean(lbla))/@stdevp(lbla) (loan-@mean(loan))/@stdevp(loan) (oil-@mean(oil))/@stdevp(oil) (orders-@mean(orders))/@stdevp(orders)
stom(group03, ff)
matrix scores = ff*evec
As noted in the manual
Code: Select all
Note that when computing scores using Equation (12.33), EViews will transform the Y to match the data used in the original computation. For example, the data will be scaled for analysis of correlation matrices, and partialing will remove means and any conditioning variablesgroup01.makepcomp(eigvec=evec) a1 a2 a3
group group02 a1 a2 a3
group group03 (lbla-@mean(lbla))/@stdevp(lbla) (loan-@mean(loan))/@stdevp(loan) (oil-@mean(oil))/@stdevp(oil) (orders-@mean(orders))/@stdevp(orders)
stom(group03, ff)
matrix scores = ff*evec