Time varying effects models and state space models are frequently used in space-time analysis of survey data. But rarely we recognize what is the best possible approach to the survey data estimation and analysis. The choice for one of the two kind of models depends on the amount of information delivered by the parameters estimates and their particular characteristics. The state space models seems to give a more amount of information, because of its updated-by-time set of parameters. This presentation will analyze what real data analysis suggests for efficiency, and what comes from the estimation of that efficiency of both models (in the context of known area units) based only on sample data
Spatio-temporal time-varying effects models and state-space models with spatial structure: an assessment of their efficiency in small area estimation
SALVATORE, Renato
2014-01-01
Abstract
Time varying effects models and state space models are frequently used in space-time analysis of survey data. But rarely we recognize what is the best possible approach to the survey data estimation and analysis. The choice for one of the two kind of models depends on the amount of information delivered by the parameters estimates and their particular characteristics. The state space models seems to give a more amount of information, because of its updated-by-time set of parameters. This presentation will analyze what real data analysis suggests for efficiency, and what comes from the estimation of that efficiency of both models (in the context of known area units) based only on sample dataI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
