Getting factor estimates from Dynamic Factor Model (DFM)

[TINA PARATE]

dfactor (variable_name1 variable_name2 variable_name3 variable_name4) (f=, ar(1)), nolog

predict f1, factor

After I use the first command to run the DFM model keeping AR 1 and letting STATA decide on the no. of factors, when I use the second command to generate the factor estimates, I only get single series of factors. When I write 'predict f1 f2 f3, factor' like PCA commands it does'nt accept that.

I wanted to know whether we can get more than one factor estimates? Or it only generates one? Or is it that for my data there is a single latent (Unobserved) factor only and that the second command usually generates all the applicable number of factors?

Also, if I want to generate an index from DFM then is the generated series in data editor my index? Do I have to interpret anything from DFM results (could not attach due to technical error)? How do we check model significance for variables?

Please if anyone could help
Thanks

[George Ford]

From the help file:

use http://www.stata-press.com/data/r12/dfex.dta , clear

dfactor (D.(ipman income hours unemp) = , noconstant) (f = , ar(1/2))
tsappend, add(6)

predict Dipman_f, dynamic(tm(2008m12)) equation(D.ipman)
predict Dincome_f, dynamic(tm(2008m12)) equation(D.income)