Imputation problem

Dear all:

I am working with data from a large cohort study in which participants were asked, retrospectively, about their work history. Data are structured such that there is one observation (row) per study participant.

I am using mi impute in stata (version 12) to multiply impute variables (using MICE). I am having trouble imputing variables that represent the start and end years for conducting a task (I am using intreg). Some participants in the data set are missing start date values, some are missing end date values, and some are missing both.



set more off
mi set mlong
mi register imputed START_YEAR END_YEAR
mi register regular CANCER_EVENT FOLLOW_UP_YEARS birth_place
mi impute chained (truncreg, cond (if TASK==1) ll (YEAR_TEN) ul(UPPER_LIMIT_START)) START_YEAR
(truncreg, cond (if TASK==1) ll (LOWER_LIMIT_END) ul(ENROLLMENT_YEAR)) END_YEAR =CANCER_EVENT FOLLOW_UP_YEARS i.birth_place, add(1) rseed(2332) force noisily

I receive the following error message:
st_store(): 3203 colvector required
_Imp_intreg::fillmis(): - function returned error
<istmt>: - function returned error
error occurred during imputation of START_YEAR END_YEAR on m = 1

I will appreciate any ideas you have for ways to solve this problem.


Thank you in advance!