Hungarian tax – benefit microsimulation model
The microsimulation procedure examines social and economic changes by assessing the effect of each provision by small units – in our case, households – and the description of the overall effects is derived from these. The relevance of the results for the society as a whole is ensured by the database being a national representative sample of the units or households of such size that guarantees the required statistical reliability. Naturally, the range of social and economic changes that can be modelled this way is defined by the information available on the microsimulation units in the database. In addition to the generally used social and demographic variables the microsimulation database contains detailed information on households related to five areas: income, consumption, taxation, participation in various social transfers and job market position.
No survey is available
that examines the above five areas in the required detail from all aspects.
The execution of a survey like that is not only very costly and time consuming,
but would not be reasonable due to reliability aspects, either. For these
reasons we have created the microsimulation database by merging various
data sets. The sets that were used are: the Monitor of TÁRKI, the Household
Budget survey of Central Statistical Office and the actual (anonymous)
tax returns from the APEH (Internal/Inland Revenue Service) database. These
sets naturally contain the data of different samples; accordingly, the
most difficult technical task when creating the database was merging the
different data sets. This involved a procedure during which attributes
could be assigned to the actual household of one data set that were not
available in the given data set, but were available on many other households
of another data set. The criteria of how well the matching works is whether
the attributes assigned to the given household come from a household of
the other data set that is similar to the one we are assigning to in the
most significant aspects. At the same time, since the assigned data are
not actually known for the same household, these have to be values that
are not constant and show some distribution. We have selected the multiple
imputation method for solving this task from among the many available statistical
Multiple imputation is a procedure generally used for managing the problem of missing data, where the missing data are substituted not single values, but more than one values, the distribution of which is as close as possible to the distribution from which the missing data would come. In practice, multiple copies of the data set (hence the term “multiple”) are created and the one containing the gaps in the data is created, and the missing data is replaced by different values in each set (hence the term “imputation”). The analysis to be performed is executed on all data sets created in this way, and the average of the results will be the result of the analysis based on multiple imputation. The basic idea behind multiple imputation is used when creating the microsimulation database so that the non-existing data of households in one data set (TÁRKI Monitor) that exist in other sets (such as consumption data in the CSO Household Budget survey) are considered as missing data and are replaced from these sets. For households providing supplementary data (donors) to be as similar to the original households as possible, we define categories based on social and demographic data existing in both surveys. Using these categories, we can replace the missing attributes of the original household (recipient) with the data of the donor households which are suitable from the most aspects. This procedure is multiple imputation based on dynamic matching. The application of multiple imputation is optimal from the point of view of the errors created during matching, but results in a complex data structure that requires special programs to manage it.
We have selected the MS
Access database management system as the software tool for modelling on
the microsimulation database, but Access need not be installed on a computer
to be anble to run the microsimulation program.
The structure of the microsimulation model:
The same methodology can be applied to data from other countries and for international comparison.
In the case of interest,
TÁRKI H-1118 Budapest, Budaörsi út 45. 36/1/309-7660