structure of mlm objects ?

I am using the function "lm" to fit several responses at the same time (100
responses). At the end of the fit, I get an object of class "mlm".

Actually of class c("mlm", "lm").

I would like to know if there is a way to access to each of the 100
underlying models separately (is it a list, ... ?). Which syntax should I
use to see and use the 15th model (for instance) just like it is possible
for classical "lm" objects.

You don't have 100 underlying fits.  All the information is for one set 
of x's and 100 sets of y, and that relating only to x is stored only once.
The following simple function will extract the i'th fit.

mlm2lm <- function(fit, i)
{
    for(k in c("coefficients", "residuals", "effects", "fitted.values"))
        fit[[k]] <- fit[[k]][, i]
    class(fit) <- "lm"
    fit
}

albeit with the wrong call, so use carefully.

Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595