

   LLooccaall RReeggrreessssiioonn,, LLiikkeelliihhoooodd aanndd DDeennssiittyy EEssttiimmaattiioonn..

        locfit(formula, data, weights, cens, base, subset, geth, ..., lfproc)

   AArrgguummeennttss::

    formula: Model Formula; e.g. `y~x' for a regression model;
             `~x' for a density estimation model

       data: Data Frame.

    weights: Prior weights (or sample sizes) for individual
             observations. This is typically used where obser-
             vations have unequal variance.

       cens: Censoring indicator. `1' (or `TRUE') denotes a
             censored observation.  `0' (or `FALSE') denotes
             uncensored.

       base: Baseline for local fitting. For local regression
             models, specifying a `base' is equivalent to using
             `y-base' as the reponse. But `base' also works for
             local likelihood.

     subset: Subset observations in the data frame.

       geth: Don't use.

        ...: Other arguments to `locfit.raw()' (or the
             `lfproc').

     lfproc: A processing function to compute the local fit.
             Default is `locfit.raw()'. Other choices include
             `locfit.robust()', `locfit.censor()' and `loc-
             fit.quasi()'.

   VVaalluuee::

        An object with class `"locfit"'. A standard set of
        methods for printing, ploting, etc. these objects is
        provided.  `locfit()' is a model-formula based front
        end to `locfit.raw()'.

   RReeffeerreenncceess::

        Consult the Web page <URL: http://cm.bell-
        labs.com/stat/project/locfit/>.

   SSeeee AAllssoo::

        `locfit.raw'

   EExxaammpplleess::

        locfit(NOx~E,data=ethanol)

