

   FFuunnccttiioonn ttoo ccoommppuuttee rraannkkss ffrroomm tthhee dduuaall ((rreeggrreessssiioonn
   rraannkkssccoorree)) pprroocceessss

        ranks(v, score="wilcoxon")

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

          v: regression quantile structure for the model of
             interest

      score: The score function desired.  Currently implemented
             score functions are Wilcoxon, Normal, and Sign
             which are asymptotically optimal for the logistic,
             Gaussian and Laplace error models respectively.

   DDeessccrriippttiioonn::

   DDeettaaiillss::

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

        The function returns two components one is the ranks,
        the other is a scale factor which is the L_2 norm of
        the score function.  All score functions should be nor-
        malized to have mean zero.

   SSiiddee EEffffeeccttss::

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

        Gutenbrunner, C., J. Jureckova,  Koenker, R. and  Port-
        noy, S.(1993) Tests of Linear Hypotheses  based on
        Regression Rank Scores", Journal of Nonparametric
        Statistics, (2), 307-331.

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

        See also rq, rrs.test

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

        data(stackloss)
        ranks(rq(stack.x,stack.loss))

