lpeAdj                package:LPEadj                R Documentation

_H_i_g_h _l_e_v_e_l _l_p_e_A_d_j _f_u_n_c_t_i_o_n _t_h_a_t _e_x_e_c_u_t_e_s _t_h_e _a_d_j_u_s_t_e_d _l_o_c_a_l _p_o_o_l_e_d
_e_r_r_o_r _s_i_g_n_i_f_i_c_a_n_c_e _t_e_s_t. _I_f _m_o_r_e _c_o_n_t_r_o_l _o_v_e_r _p_a_r_a_m_e_t_e_r_s _i_s _n_e_e_d_e_d
_t_h_e_n _s_e_e _d_o_c_u_m_e_n_t_a_t_i_o_n _f_o_r _c_a_l_c_u_l_a_t_e_L_p_e_A_d_j.

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

     Applies the LPE algorithm with two additional options. The first
     is that the original LPE method sets all variances below the max
     variance in the ordered distribution of variances to the maximum
     variance. in LPEadj this option is turned off by default.  The
     second option is to use a variance adjustment based on sample size
     rather than pi/2. By default the LPEadj uses the sample size based
     variance adjustment.  It is recommended to keep both of these
     options to the default.

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

       lpeAdj(dat, labels=NULL, doMax=FALSE, doAdj=TRUE, q=.01)

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

     dat: Replicated data of experiment containing two groups (as
          matrix  or data-frame)

  labels: vector of group labels that correspond to the columns of dat.
          eg. labels=c(0,0,0,1,1,1) describes two groups with three
          replicates each

   doMax: boolean: if T then all variances below the max variance in
          the ordered distribution of variances are set to the maximum
          variance. It is recommended to use the default value of
          False.

   doAdj: If T then run LPE with using variance adjustment value based
          on number of replicates (hardcoded in adjValues) rather than
          pi/2.

       q: is the quantile width; q=0.01 corresponds to 100 quantiles
          i.e. percentiles. Bins/quantiles have equal number of genes
          and are split according to the average intensity A.

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

     The LPE test statistic numerator is the difference in medians
     between the two experimental conditions. The test statistic
     denominator is the combined pooled standard error for the two
     experimental conditions obtained by looking up the var.M from each
     baseOlig.error variance function. The conversion to p-values is
     based on the Gaussian distribution for difference if order
     statistics (medians).

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

     Data frame including x, median of x, y, median of y, median
     difference of (x,y), pooled standard deviation of difference, LPE
     p-value, outlier flag, probability of an outlier within x or y, .

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

     Carl Murie carl.murie@mcgill.ca,  Nitin Jain nitin.jain@pfizer.com

_R_e_f_e_r_e_n_c_e_s:

     J.K. Lee and M.O.Connell(2003). _An S-Plus library for the
     analysis of differential expression_. In The Analysis of Gene
     Expression Data: Methods and Software. Edited by G. Parmigiani, ES
     Garrett, RA Irizarry ad SL Zegar. Springer, NewYork.

     Jain et. al. (2003) _Local pooled error test for identifying
     differentially expressed genes with a small number of replicated
     microarrays_, Bioinformatics, 1945-1951.

     Jain et. al. (2005) _Rank-invariant resampling based estimation of
     false discovery rate for analysis of small sample microarray
     data_, BMC Bioinformatics, Vol 6, 187.

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

        
      # Loading the library and null dataset (two groups with three
      # replicates each)
      library(LPEadj)
      dat <- matrix(rnorm(6000), ncol=6)
      
      # Applying LPE
      lpe.result <- lpeAdj(dat, labels=c(0,0,0,1,1,1))
       

