Title: Small area estimation Speaker: Domingo Morales Affiliation: Instituto Universitario Centro de Investigación Operativa. Universidad Miguel Hernández de Elche. Abstract: Statistical Offices design surveys to estimate population parameters and select sample sizes to achieve an a priori fixed precision.In practice, statisticians are often required to give estimates of subpopulations or small areas, where sample sizes are small.Direct estimators of small area parameters, calculated using only the sample data from the corresponding area, are not reliable enough. The use of models that include auxiliary variables and borrow strength from cross-sectional data or time and spatial correlation may produce estimates that are more accurate. Small Area Estimation is a part of statistical science that improves the efficiency of direct estimators by combining methodologies from survey sampling and finite population inference with statistical models.The talk introduces the model-based approaches and outlines some recent advances related to empirical best predictors of small area bivariate parameters, like ratios of sums or sums of ratios. An application to real data from the Spanish household budget survey illustrates the statistical methodology by giving estimators of ratios of food household expenditures by provinces.