estimTdiff            package:smoothSurv            R Documentation

_E_s_t_i_m_a_t_e _e_x_p_e_c_t_a_t_i_o_n _o_f _s_u_r_v_i_v_a_l _t_i_m_e_s _a_n_d _t_h_e_i_r _d_i_f_f_e_r_e_n_c_e _f_r_o_m _t_h_e
_r_e_s_u_l_t_s _g_i_v_e_n _b_y _s_u_r_v_i_v_a_l _r_e_g_r_e_s_s_i_o_n _f_u_n_c_t_i_o_n

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

     Estimate expectation of survival times and their difference from
     the results given by survival regression function

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

     estimTdiff(x, ...)
     ## S3 method for class 'smoothSurvReg':
     estimTdiff(x, cov1, cov2, logscale.cov1, logscale.cov2, time0 = 0, ...)

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

       x: Object of an appropriate class. 

    cov1: Vector or matrix with covariates values for which the
          expectations of the first survival time are to be computed.
          It must be a matrix with as many  columns as is the number of
          covariates (interactions included, intercept excluded)  or
          the vector of length equal to the number of covariates
          (interactions included, intercept excluded). If matrix is
          supplied then is assumed that each row of this matrix gives
          one covariate combination for the first survival time.
          Intercept is not to be included in 'cov1'. If 'cov1' is
          missing an expectation of a survivor time for the value of a
          covariate vector equal to zero is computed. If there is only
          intercept in the model, this parameter must be always
          missing. 

    cov2: Vector or matrix with covariate values for which the
          expectations of the second survival time are to be computed.
          It must be of same size as 'cov1'. 

logscale.cov1: Vector or matrix with covariate values for the
          expression of log-scale (if this depended on covariates) for
          the first survival time.  It can be omitted in the case that
          log-scale was common for all observations.  

logscale.cov2: Vector or matrix with covariate values for the
          expression of log-scale (if this depended on covariates) for
          the second survival time.  It can be omitted in the case that
          log-scale was common for all observations.  

   time0: Starting time of the follow-up as used in the model. I.e. the
          model is assumed to be log(T-time0) = x'beta + sigma*epsilon  

     ...: who knows 

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

     A 'data.frame' with columns named ``ET1'', ``sd.ET1'', ``ET2'',
     ``sd.ET2'', ``diffT'', ``sd.diffT'' giving the estimates of
     expected values of the survival times for covariate values given
     in rows of 'cov1' and 'logscale.cov1',  their standard errors,
     estimates of expected values of survival times for covariate
     values given in rows of 'cov2'  and 'logscale.cov2', their
     standard errors and estimates of a difference of expected values
     of survival times for covariate values given in rows of 'cov1',
     'logscale.cov1' and 'cov2', 'logscale.cov2'  and their standard
     errors.

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

     Arno&#353t Kom&#225rek komarek@karlin.mff.cuni.cz

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

     'smoothSurvReg'

