OutlierD              package:OutlierD              R Documentation

_O_u_t_l_i_e_r _d_e_c_t_e_c_t_i_o_n _u_s_i_n_g _q_u_a_n_t_i_l_e _r_e_g_r_e_s_s_i_o_n _o_n _t_h_e _M-_A _s_c_a_t_t_e_r_p_l_o_t_s _o_f _h_i_g_h-_t_h_r_o_u_g_h_p_u_t _d_a_t_a

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

     This detects outliers using quantile regression on the M-A
     scatterplots of high-throughput data.

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

          OutlierD(x1, x2, k=1.5, method="nonlin")

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

      x1: one n-by-1 vector for data (n= number of peptides, proteins,
          or genes

      x2: the other n-by-1 vector for data (n= number of peptides,
          proteins, or genes

       k: parameter in Q1-k*IQR and Q3+k*IQR, IQR=Q3-Q1, k=1.5
          (default)

  method: one of constant, linear, nonlinear, and nonparametric
          quantile regression

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

       x: data and results for outliers

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

     HyungJun Cho

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

     data(lcms)
     x <- log2(lcms) #log2-tranformation, do normalization if necessary

     fit1 <- OutlierD(x1=x[,1], x2=x[,2], method="constant")
     fit2 <- OutlierD(x1=x[,1], x2=x[,2], method="linear")
     fit3 <- OutlierD(x1=x[,1], x2=x[,2], method="nonlin")
     fit4 <- OutlierD(x1=x[,1], x2=x[,2], method="nonpar")

     fit3$x[1:10,]

     plot(fit3$x$A, fit3$x$M, pch=".", xlab="A", ylab="M")
     i <- sort.list(fit3$x$A)
     lines(fit3$x$A[i], fit3$x$Q3[i], lty=2); lines(fit3$x$A[i], fit3$x$Q1[i], lty=2)
     lines(fit3$x$A[i], fit3$x$LB[i]); lines(fit3$x$A[i], fit3$x$UB[i])
     title("Nonlinear")

