classifyTests             package:limma             R Documentation

_T_r_e_a_t _S_i_m_u_l_t_a_n_e_o_u_s _T-_T_e_s_t_s _a_s _C_l_a_s_s_i_f_i_c_a_t_i_o_n _P_r_o_b_l_e_m

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

     Classify a series of related t-statistics as up, down or not
     significant.

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

     classifyTests(tstat, cor.matrix=NULL, design=NULL, contrasts=NULL, df=Inf, p.value=0.01)
     classifyTestsT(tstat, t1=4, t2=3)
     classifyTestsP(tstat, df=Inf, p.value=0.05, method="holm")

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

   tstat: numeric matrix of t-statistics or an 'MArrayLM' object from
          which the t-statistics may be extracted.

cor.matrix: covariance matrix of each row of t-statistics.  Defaults to
          the identity matrix.

  design: full rank numeric design matrix.  Not used if 'cor.matrix' is
          specified.

contrasts: numeric matrix with columns specifying contrasts of the
          coefficients of interest.  Not used if 'cor.matrix' is
          specified.

      df: numeric vector giving the degrees of freedom for the
          t-statistics. May have length 1 or length equal to the number
          of rows of 'tstat'.

 p.value: numeric value between 0 and 1 giving the desired size of the
          test

      t1: first critical value for absolute t-statistics

      t2: second critical value for absolute t-statistics

  method: character string specifying p-value adjustment method.  See
          'p.adjust' for possible values.

_D_e_t_a_i_l_s:

     'classifyTests' classifies using a nested F-test approach giving
     particular attention to correctly classifying genes which have two
     or more significant t-statistics, i.e., are differential expressed
     under two or more conditions. 'classifyTestsT' and
     'classifyTestsP' implement simpler classification schemes based on
     threshold or critical values for the individual t-statistics in
     the case of 'classifyTestsT' or p-values obtained from the
     t-statistics in the case of 'classifyTestsP'.

     Rows of 'tstat' correspond to genes and columns to coefficients or
     contrasts. For each row of 'tstat', F-statistics are constructed
     from the t-statistics. If the overall F-statistic is significant,
     then the function makes a best choice as to which t-statistics
     contributed to this result. The methodology is based on the
     principle that any t-statistic should be called significant if the
     F-test is still significant for that row when all the larger
     t-statistics are set to the same absolute size as the t-statistic
     in question.

     If 'tstat' is an 'MArrayLM' object, then all arguments except for
     'p.value' are extracted from it.

     'cor.matrix' is the same as the correlation matrix of the
     coefficients from which the t-statistics are calculated. If
     'cor.matrix' is not specified, then it is calculated from 'design'
     and 'contrasts' if at least 'design' is specified or else defaults
     to the identity matrix. In terms of 'design' and 'contrasts',
     'cor.matrix' is obtained by standardizing the matrix '
     t(contrasts) %*% solve(t(design) %*% design) %*% contrasts ' to a
     correlation matrix.

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

     A list with components 

classification: numeric matrix with elements '-1', '0' or '1' depending
          on whether each t-statistic is classified as significantly
          negative, not significant or significantly positive
          respectively

   Fstat: numeric vector containing moderated F-statistics for testing
          the contrasts simultaneously zero

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

     Gordon Smyth

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

     An overview of linear model functions in limma is given by
     5.LinearModels.

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

     tstat <- matrix(c(0,5,0, 0,2.5,0, -2,-2,2, 1,1,1), 4, 3, byrow=TRUE)
     classifyTests(tstat)

     # See also the examples for contrasts.fit and vennDiagram

