pool                  package:mice                  R Documentation

_M_u_l_t_i_p_l_e _I_m_p_u_t_a_t_i_o_n _P_o_o_l_i_n_g

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

     Pools the results of m repeated complete data analysis

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

     pool(object, method="smallsample")

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

  object: An object of class 'mira', produced by functions like lm.mids
          or glm.mids.

  method: A string describing the method to compute the degrees of
          freedom.  The default value is "smallsample", which specifies
          the is  Barnard-Rubin adjusted degrees of freedom (Barnard&
          Rubin, 1999)  for small samples. Specifying a different
          string  produces the conventional degrees of freedom as in
          Rubin (1987).

_D_e_t_a_i_l_s:

     The function averages the estimates of the complete data model, 
     computes the total variance over the repeated analyses, and
     computes the relative increase in variance due to nonresponse and
     the fraction  of missing information. The function relies on the
     availability of

        1.  the estimates of the model, typically present as
           'coefficients' in  the fit object

        2.  an appropriate estimate of the variance-covariance matrix
           of the  estimates per analyses.

     R-Specific: The original use of Varcov has been removed to vcov
     (VR MASS).

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

     An object of class 'mipo', which stands for 'multiple imputation
     pooled'.

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

     Stef van Buuren, Karin Oudshoorn, 2000

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

     Barnard, J. and Rubin, D.B. (1999). Small sample degrees of
     freedom with multiple imputation. Biometrika, 86, 948-955.

     Rubin, D.B. (1987). Multiple Imputation for Nonresponse in
     Surveys.  New York: John Wiley and Sons.

     Alzola, C.F. and Harrell, F.E. (1999). An introduction to S-Plus
     and the Hmisc  and Design Libraries.
     http://hesweb1.med.virginia.edu/biostat/s/index.html.

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

     'lm.mids', 'glm.mids', 'vcov', 'print.mira', 'summary.mira'

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

     data(nhanes)
     imp <- mice(nhanes)
     fit <- lm.mids(bmi~hyp+chl,data=imp)
     pool(fit)
     #  Call: pool(object = fit)
     #  Pooled coefficients:
     #   (Intercept)       hyp        chl 
     #      21.29782 -1.751721 0.04085703
     #
     #  Fraction of information about the coefficients missing due to nonrespons
     #  e: 
     #   (Intercept)       hyp       chl 
     #     0.1592247 0.1738868 0.3117452
     #
     #  > summary(pool(fit))
     #           est         se          t       df     Pr(>|t|) 
     #  (Intercept)  21.29781702 4.33668150  4.9110863 16.95890 0.0001329371
     #      hyp  -1.75172102 2.30620984 -0.7595671 16.39701 0.4582953905
     #      chl   0.04085703 0.02532914  1.6130442 11.50642 0.1338044664
     #             lo 95      hi 95 missing       fmi 
     #  (Intercept)  12.14652927 30.4491048      NA 0.1592247
     #      hyp  -6.63106456  3.1276225       8 0.1738868
     #    chl  -0.01459414  0.0963082      10 0.3117452 

