plotPredChecks             package:BGmix             R Documentation

_P_l_o_t_s _o_f _p_r_e_d_i_c_t_i_v_e _c_h_e_c_k_s _f_o_r _m_i_x_t_u_r_e _p_r_i_o_r.

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

     Histograms and q-q plots of predictive p-values for the mixture
     prior. Separate plots are given for each mixture component, using
     only genes with high posterior probability of being classified
     into the relevant component.

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

     plotPredChecks(pvals, pc, probz = 0.8, label = "", breaks = 20)

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

   pvals: matrix of predictive p-values output by 'ccPred' (NB, not the
          whole list object, just the matrix of p-values)

      pc: matrix of posterior classification probabilities output by
          'ccParams' (NB, not the whole list object, just the matrix of
          probabilities)

   probz: threshold on posterior probabilities for including genes in
          each mixture component plot

   label: title used on histograms

  breaks: argument input to histogram

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

     Alex Lewin

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

     ## Note this is a very short MCMC run!
     ## For good analysis need proper burn-in period.
     data(ybar,ss)
     outdir <- BGmix(ybar, ss, c(8,8), nburn=0, niter=100, nthin=1)
     params <- ccParams(outdir)
     pred <- ccPred(outdir)
     plotPredChecks(pred$pval.ybar.mix2,params$pc,probz=0.5)

