EN
In the paper the results of small area estimation using empirical best linear unbiased predictor (EBLUP) for the data coming from Polish Household Budget Survey are presented. The results were obtained using small area models of household expenditures for regions. Estimation of sampling errors was conducted by means of the balanced repeated replication (BRR) technique. The estimation of EBLUPs and their corresponding mean square errors (MSE) was carried out using variance components technique. To calculate MSE of EBLUP the maximum likelihood method (ML) and restricted maximum likelihood method (REML) were used. The computation was made using SAE package designed for R-project.