

survexp(survival4)                           R Documentation

_C_o_m_p_u_t_e _E_x_p_e_c_t_e_d _S_u_r_v_i_v_a_l

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

     Individual expected survival is ususally used in models
     or testing, to `correct' for the age and sex composi-
     tion of a group of subjects.  For instance, assume that
     birth date, entry date onto the study,sex and actual
     survival time are all known for a group of subjects.
     The uswhite population tables contain expected death
     rates based on calendar year, sex and age.  Then haz <-
     -log(survexp(death.time ~ ratetable(sex=sex,
     year=entry.dt, age=(birth.dt-entry.dt)), cohort=F))
     gives for each subject the total hazard experienced up
     to their observed death time or censoring time.  This
     probability can be used as a rescaled time value in
     models: glm(status ~ 1 + offset(log(haz)), family=pois-
     son) glm(status ~ x + offset(log(haz)), family=poisson)
     In the first model, a test for intercept=0 is the one
     sample log-rank test of whether the observed group of
     subjects has equivalent survival to the baseline popu-
     lation.  The second model tests for an effect of vari-
     able `x' after adjustment for age and sex.

     Cohort survival is used to produce an overall survival
     curve.  This is then added to the Kaplan-Meier plot of
     the study group for visual comparison between these
     subjects and the population at large.  There are three
     common methods of computing cohort survival.  In the
     "exact method" of Ederer the cohort is not censored;
     this corresponds to having no response variable in the
     formula.  Hakulinen recommends censoring the cohort at
     the anticipated censoring time of each patient, and
     Verhuel recommends censoring the cohort at the actual
     observation time of each patient.  The last of these is
     the conditional method.  These are obtained by using
     the respective time values as the follow-up time or
     response in the formula.

_U_s_a_g_e_:

     survexp(formula, data, weights, subset, na.action,
      times, cohort=T, conditional=T,
      ratetable=survexp.us, scale=1, se.fit, model=F, x=F, y=F)

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

 formula: a formula object.  The response variable will be a
          vector of follow-up times, and is optional.  The
          predictors will consist of optional grouping vari-
          ables separated by + operators (exactly as in
          `survfit'), along with a `ratetable()' term.  This
          latter matches each subject to his/her expected
          cohort.

   data,: as in other modeling routines.  Weights are cur-
          rently ignored.

   times: an optional vector of times at which the resulting
          survival curve should be evaluated.  If absent,
          the result will be reported for each unique value
          of the vector of follow-up times.

  cohort: If false, each subject is treated as a subgroup of
          size 1.

conditional: If `y' is missing in the formula, this argument
          is ignored.  Otherwise it is an indicator of
          whether y includes death times, which leads to
          conditional expected survival, or y includes only
          the potential censoring times.

ratetable: a table of event rates, such as survexp.uswhite,
          or a fitted Cox model.

   scale: a scaling for the results.  As most rate tables
          are in units/day, a value of 365.24 would cause
          the output to be reported in years.

 npoints: calculate intermediate results at npoints values,
          evenly spaced on the range of `y'.  The usual
          (exact) calculation is done at each unique 'y'
          value; for very large data sets this may incur too
          much storage for the scratch array.  For a predic-
          tion from a Cox model this arument is ignored.

  se.fit: compute the standard error of the predicted sur-
          vival.  The default is to compute this whenever
          the routine can, which at this time is only for
          the Ederer method and a Cox model as the rate
          table.

  model,: flags to control what is returned.  If any of
          these is true, then the model frame, the model
          matrix, and/or the vector of response times will
          be returned as components of the final result,
          with the same names as the flag arguments.

_V_a_l_u_e_:

     if cohort=T an object of class `survexp', otherwise a
     vector of per-subject expected survival values.  The
     former contains the number of subjects at risk and the
     expected survival for the cohort at each requested
     time.

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

     G. Berry.  The analysis of mortality by the subject-
     years method.  Biometrics 1983, 39:173-84.  F Ederer, L
     Axtell, and S Cutler.  The relative survival rate: a
     statistical methodology. Natl Cnacer Inst Monogr 1961,
     6:101-21.  T. Hakulinen.  Cancer survival corrected for
     heterogeneity in patient withdrawal.  Biometrics 1892,
     38:933.  H. Verheul, E. Dekker, P. Bossuyt, A. Moulijn,
     and A. Dunning.  Backround mortality in clinical sur-
     vival studies.  Lancet 1993, 341:872-5.

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

     `survfit', `survexp.us', `survexp.fit', `personyr',
     `date'

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

     library(ratetables)
     data(jasa)
     efit <- survexp( ~ ratetable(sex=sex, year=entry.dt, age=entry.dt-birth.dt))
     plot(survfit(Surv(futime, status) ~1))
     lines(efit)

