A three-level M-quantile model for poverty mapping in Poland

Poverty mapping is of crucial signicance in many countries all over the world, including Poland. EU-SILC is the main source of information about poverty but data from this survey are only sucient to publish poverty indicators at country and regional level (NUTS 1). This is the consequence of small sample sizes in dierent domains, which causes a low precision of estimation. Given the small sample size in relevant cross clas- sications of the EU-SILC survey, it is, therefore, necessary to use the latest techniques of indirect estimation and draw on alternative data sources to estimate the parameters of interest at low levels of spatial aggregation with acceptable precision. One of the methods which can be practically employed for deriving small area estimates of poverty and inequality is the M-quantile technique.