We introduce a command, fayherriot, that implements the Fay–Herriot model (Fay and Herriot, 1979, Journal of the American Statistical Association 74: 269–277), which is a small-area estimation technique (Rao and Molina, 2015, Small Area Estimation), in Stata. The Fay–Herriot model improves the precision of area-level direct estimates using area-level covariates. It belongs to the class of linear mixed models with normally distributed error terms. The fayherriot command encompasses options to a) produce out-of-sample predictions, b) adjust nonpositive random-effects variance estimates, and c) deal with the violation of model assumptions.
Keywords: st0570, fayherriot, disaggregated indicators, small-area estimation, (log-transformed) Fay–Herriot model, empirical best linear unbiased predictor