|
This project exploits cross-country variation in the availability of administrative information to impute missing household wealth items in the Household Finance and Consumption Survey (HFCS). Using tools from Machine Learning, I train an imputation algorithm on an artificial counterfactual dataset constructed from country surveys where the use of administrative information leads to low numbers of missing items. I then apply this algorithm to impute missing wealth items in those HFCS country surveys which have high rates of them.
The project’s contributions are twofold: First, I seek to explore an imputation method which allows sharing the benefits of country-specific register data with countries using surveys. As the number of HFCS countries which augment their surveys with quasi-administrative data is foreseen to increase but to remain modest, I provide a complementary perspective to the current imputation. Second, given that the ratio of liquid versus illiquid assets has been shown to matter for the transmission and redistributional effects of fiscal and monetary policies, I investigate the sensitivity of measures on Euro Area household wealth.
|
