GetRepeatRanking        package:GeneSelector        R Documentation

_R_e_p_e_a_t _t_h_e _r_a_n_k_i_n_g _p_r_o_c_e_d_u_r_e _f_o_r _a_l_t_e_r_e_d _d_a_t_a _s_e_t_s

_D_e_s_c_r_i_p_t_i_o_n:

     Altered data sets are typically prepared by calls to
     GenerateFoldMatrix or GenerateBootMatrix. The ranking procedure is
     then repeated for each of these new 'artificial' altered data
     sets. One major goal of this procedure is to examine the stability
     of the results obtained with the original dataset.

_U_s_a_g_e:

     GetRepeatRanking(R, P, scheme=c("Subsampling", "Labelexchange"), iter=10, 
                                   varlist = list(genewise=FALSE, factor=1/5), ...)

_A_r_g_u_m_e_n_t_s:

       R: The original ranking, represented by an object of class
          GeneRanking.

       P: An object of class FoldMatrix or BootMatrix as generated by
          GenerateFoldMatrix or GenerateBootMatrix, respectively.
           Can also be 'missing'. In this case, the original dataset is
          perturbed by adding gaussian noise, s. argument 'varlist'.

  scheme: Used only if 'P' is a 'Foldmatrix'. Can be '"Subsampling"' or
          '"Labelexchange"'. 'Subsampling' means that observations are
          removed as determined by the slot 'foldmatrix'. 
          'Labelexchange' means that those observations which would be
          removed are instead kept in the sample, but are assigned to
          the opposite class.

    iter: Used only if 'P' is missing, specifying the number of
          different noise-perturbed datasets to be created. Per
          default, the number of iterations is 10.

 varlist: Used only if 'P' is missing. A list with two components
          ('genewise', a logical and 'frac', a positive real number),
          both controlling the variance of the added noise. If 
          'genewise=FALSE' (default) then the noise has the same
          variance for all genes: it is estimated by pooled variance
          estimation from the original data set. Otherwise, the
          variance of the noise is different for each gene and
          estimated genewise from the original data set. 'frac' is the
          fraction of the variance of the estimated variance(s) to be
          used as the variance of the added noise. The default value is
          '1/5' and is usually clearly smaller than 1.

     ...: Further arguments to be passed to the Ranking method from
          which rankings are generated.

_V_a_l_u_e:

     An object of class RepeatRanking

_A_u_t_h_o_r(_s):

     Martin Slawski martin.slawski@campus.lmu.de 
      Anne-Laure Boulesteix <URL: http://www.slcmsr.net/boulesteix>

_S_e_e _A_l_s_o:

     GeneRanking, RepeatRanking, RankingTstat, RankingFC,
     RankingWelchT, RankingWilcoxon, RankingBaldiLong,
     RankingFoxDimmic, RankingLimma,  RankingEbam, RankingWilcEbam,
     RankingSam,  RankingBstat, RankingShrinkageT,
     RankingSoftthresholdT,  RankingPermutation, RankingGap

_E_x_a_m_p_l_e_s:

      ## Load toy gene expression data
     data(toydata)
     ### class labels
     yy <- toydata[1,]
     ### gene expression
     xx <- toydata[-1,]
     ### Get ranking for the original data set, with the ordinary t-statistic
     ordT <- RankingTstat(xx, yy, type="unpaired")
     ### Generate the leave-one-out / exchange-one-label matrix
     loo <- GenerateFoldMatrix(xx, yy, k=1)
     ### Repeat the ranking with the t-statistic, using the leave-one-out scheme
     loor_ordT <- GetRepeatRanking(ordT, loo)
     ### .. or the label exchange scheme
     ex1r_ordT <- GetRepeatRanking(ordT, loo, scheme = "Labelexchange")
     ### Generate the bootstrap matrix
     boot <- GenerateBootMatrix(xx, yy, maxties=3, minclassize=5, repl=30)
     ### Repeat ranking with the t-statistic for bootstrap replicates
     boot_ordT <- GetRepeatRanking(ordT, boot)
     ### Repeat the ranking procedure for an altered data set with added noise
     noise_ordT <- GetRepeatRanking(ordT, varlist=list(genewise=TRUE, factor=1/10))

