Notes mostly to myself	{Martin Mchler}
----------------------------------------

1. `bug' (not really : just needs large options(expression = 20000)
    prt.vvec  {but that's an experimental function}

  look at
     example(summary.vlmc)
     print(svb, vvec.p = TRUE)

2. *do* write
     as.dendrogram.vlmc()  and  then  plot.vlmc() from it


3. require(MASS)  instead of having its fractions() code here -- done 2002-03-06

4. squish the {rare} deviance() <-> resid(*, type="dev") bug  -- done 2002-02-08

5. Get rid of attr(*, "flags") for predict and residuals.     -- done 2002-03-06
   Keep flags only in  predict(*, "ALL") !!

6. do AIC cutoff search internally -- or at least returning all
   cutoffs (+ df + loglik ?) where pruning happens.
