home *** CD-ROM | disk | FTP | other *** search
-
- _R_o_b_u_s_t _v_a_r_i_a_n_c_e _f_o_r _a _C_o_x _m_o_d_e_l _C_o_m_p_u_t_e_s _t_h_e _r_o_b_u_s_t
- "_s_a_n_d_w_i_c_h" _e_s_t_i_m_a_t_o_r _o_f _v_a_r_i_a_n_c_e _f_o_r _a _p_r_o_p_o_r_t_i_o_n_a_l _h_a_z_a_r_d_s
- _m_o_d_e_l, _a_n_d _r_e_t_u_r_n_s _a _c_o_p_y _o_f _t_h_e _f_i_r_s_t _a_r_g_u_m_e_n_t _w_i_t_h _t_h_e
- _r_o_b_u_s_t _v_a_r_i_a_n_c_e _a_d_d_e_d _o_n.
-
- coxph.rvar(fit, collapse)
-
- _A_r_g_u_m_e_n_t_s:
-
- fit:
- a coxph object, i.e., the result of fitting a Cox
- model.
-
- collapse:
- if the original data contained correlated observations,
- e.g., multiple data rows per subject, then this argu-
- ment contains the id vector that identifies the sub-
- groups.
-
- Value:
-
- a copy of the input, with two components added
-
- _A_r_g_u_m_e_n_t_s:
-
- robust.var:
- the robust variance estimate.
-
- rcall:
- the call to this function.
-
- the print and summary methods for coxph recognize and
- use the robust variance. The global likelihood ratio
- and score statistics are uneffected, but the global
- Wald test will now be based on the robust estimator.
- Let r be the matrix of infinitesimal influence func-
- tions, i.e., r <- residuals(fit, type='dbeta'). Then
- the robust variance is v <- t(r) %*% r. If there are
- correlated observations, the appropriate rows or r are
- first summed, and v is based on the reduced r matrix.
- There is an obvious connection with the ordinary and
- group jackknife estimates.
-
- coxph
-
- _E_x_a_m_p_l_e_s:
-
- fit <- coxph(Surv(futime, fustat) ~ age + rx +ecog.ps, data=fleming)
- fit2 <- coxph.rvar(fit)
- summary(fit2)
-
-