plotCorrPrecision           package:Hmisc           R Documentation

_P_l_o_t _P_r_e_c_i_s_i_o_n _o_f _E_s_t_i_m_a_t_e _o_f _P_e_a_r_s_o_n _C_o_r_r_e_l_a_t_i_o_n _C_o_e_f_f_i_c_i_e_n_t

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

     This function plots the precision (margin of error) of the
     product-moment linear  correlation coefficient r vs. sample size,
     for a given vector of correlation coefficients 'rho'.  Precision
     is defined as the larger of the upper confidence limit minus rho
     and rho minus the lower confidence limit.  'labcurve' is used to
     automatically label the curves.

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

     plotCorrPrecision(rho = c(0, 0.5), n = seq(10, 400, length = 100),
                       conf.int = 0.95)

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

     rho: single or vector of true correlations.  A worst-case
          precision graph results from rho=0

       n: vector of sample sizes to use on the x-axis

conf.int: confidence coefficient; default uses 0.95 confidence limits

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

     Xing Wang and Frank Harrell

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

     'rcorr','cor','cor.test'

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

     plotCorrPrecision()
     plotCorrPrecision(rho=0)

