RankProduct             package:RNAither             R Documentation

_P_e_r_f_o_r_m _a _R_a_n_k _P_r_o_d_u_c_t _t_e_s_t

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

     Performs the non-parametric rank product test on the intensity
     data.

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

     RankProduct(dataset, listofargs)

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

 dataset: an R data frame generated with 'generateDatasetFile' 

listofargs: a list containing: 

          - the number of permutations to perform to compute the
          p-values (usually 100)

          - 1 or 2, depending if the search is for a significant
          decrease or increase

          - a character string specifying the column whose values will
          be used for the test

          - a character string specifying the name of the dataset
          column to be used to define the replicate, for example '
          "GeneName"' or ' "Internal_GeneID"' 

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

     Returns a list containing

pValVec : a named vector of p-values

dataset : the dataset with an added column ' "p.value.rankproduct"'

paste("pValue.rankproduct", testType, sep="_") : the character string
          '"p.value.rankproduct"'

"Rank product test" : the character string "Rank product test"


     The p values returned are equivalent to the percentage of false
     prediction (pfp), which in theory is the equivalent of false
     discovery rate (FDR). It is possible that they are larger than 1.

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

     'Ttest', 'MannWhitney'

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

     data(exampleHeader, package="RNAither")
     data(exampleDataset, package="RNAither")

     pvals1 <- RankProduct(dataset, list(100, 1, "SigIntensity", "GeneName"))
     pValVec1 <- pvals1[[1]]
     scoredDataset1 <- pvals1[[2]]

