Hello everyone.

I am trying to do multiple imputation using mi impute chained using the syntax below. This is a simplified version of what I actually want to do.


mi impute chained (regress) imd = diag_group sex age_c_ent adm_bfr_cohort adm_1_mha_update antipsychot psychotro time_2_2nd_acute acute_care_1_yr_disc_1 adm_cohort c_cont_2 died_cohort, rseed(61044) add(10) force

But get this error message.
mi impute: invalid imputation method chained

I cannot see what the problem is. Any ideas?

All variables on the right of the = are registered as regular and imd is registered as imputed

Output from mi describe:

Style: flong
last mi update 19jun2019 09:10:50, 0 seconds ago



Obs.: complete 96
incomplete 808 (M = 0 imputations)
---------------------
total 904



Vars.: imputed: 35; ethnic(341) imd(293) f00_f09(376) f10_f19(376) f20_f29(376) f30_f39(376) f40_f48(376) f50_f59(376)
f60_f69(376) f90f98(376) f99(376) honos_f_1(431) honos_f_2(431) honos_f_3(433) honos_f_4(432)
honos_f_5(434) honos_f_6(432) honos_f_7(433) honos_f_8(450) honos_f_9(431) honos_f_10(433)
honos_f_11(431) honos_f_12(434) honos_1_1(782) honos_1_2(781) honos_1_3(782) honos_1_4(781)
honos_1_5(781) honos_1_6(782) honos_1_7(782) honos_1_8(784) honos_1_9(781) honos_1_10(782)
honos_1_11(782) honos_1_12(783)



passive: 1; num_diag_grps(250)



regular: 12; diag_group sex age_c_ent adm_bfr_cohort adm_1_mha_update antipsychot psychotro time_2_2nd_acute
acute_care_1_yr_disc_1 adm_cohort c_cont_2 died_cohort



system: 3; _mi_m _mi_id _mi_miss



(there are 547 unregistered variables)

Thanks
Louise