epilepticBC              package:glmmAK              R Documentation

_E_p_i_l_e_p_t_i_c _s_e_i_z_u_r_e_s, _B_r_e_s_l_o_w _a_n_d _C_l_a_y_t_o_n _t_r_a_n_s_f_o_r_m_e_d

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

     This data set considers information from a clinical trial of 59
     epileptics, reported by Thall and Vail (1990). For each patient,
     the number of epileptic seizures was recorded during a baseline
     period of eight weeks. Patients were then randomized to treatment
     with the anti-epileptic drug progabide, or to placebo in addition
     to standard chemotherapy. The number of seizures was then recorded
     in four consecutive two-weeks intervals.

     This is a transformed version of the original data ('epileptic')
     which allows directly to fit models described in Breslow and
     Clayton (1993) or in Kleinman and Ibrahim (1998).

     There are 4 rows in the dataset for each of 59 patients.

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

     data(epilepticBC)

_F_o_r_m_a_t:

     A data frame with 236 observations on the following 10 variables.

     '_i_d' a unique identifier for the subject in the study.

     '_v_i_s_i_t' a numeric vector giving the number of the visit, 1,2,3,
          and 4 for the four two-weeks intervals following the baseline
          measurement.

     '_s_e_i_z_u_r_e_0' a numeric vector giving the number of epileptic
          seizures in the eight-week period prior the randomization.

     '_a_g_e' a numeric vector giving the age (in years) at the entry.    

     '_S_e_i_z_u_r_e' a numeric vector giving the number of epileptic seizures
          in a given two-week interval.

     '_B_a_s_e' a numeric vector giving the transformed 'seizure0'.
          'Base'=log('seizure0'/4).

     '_T_r_t' a numeric vector giving the treatment group.    

     '_B_a_s_e._T_r_t' a numeric vector giving the interaction covariate
          'Base'*'Trt'.

     '_A_g_e' a numeric vector giving the transformed age.
          'Age'=log('age').

     '_V_i_s_i_t' a numeric vector giving the centered 'visit'.
          'Visit'=(2*'visit'-5)/10.    

_S_o_u_r_c_e:

     Thall, P. F., and Vail, S. C. (1990) Some covariance models for
     longitudinal count data with overdispersion. _Biometrics_, *46*,
     657-671.

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

     Breslow, N. E. and Clayton, D. G. (1993). Approximate inference in
     generalized linear mixed models. _Journal of the American
     Statistical Association_, *88*, 9-25.

     Kleinman, K. P. and Ibrahim, J. G. (1998). A semi-parametric
     Bayesian approach to generalized linear mixed models. _Statistics
     in Medicine_, *17*, 2579-2596.

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

     'epileptic'

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

     data(epilepticBC)
     ## maybe str(epilepticBC); plot(epilepticBC) ...

