The Least Trimmed Squares for time series (LTSts): extensions for policy support applications

Abstract International organizations need to monitor large amounts of economic and financial data to prevent or uncover potential problems in policies implementation. The analysis of such time series cannot ignore the potential presence of anomalies and structural changes. In this paper, we elaborate on a robust framework for time series analysis based on Least Trimmed Squares able to treat outliers and points where a change in level takes place. We enhance the flexibility of the model by introducing new terms in its definition and extend its applicability to cases with missing observations and multiple level shifts. Moreover, we study its properties, propose a variable selection procedure and introduce instruments for its use in operationally intensive environments requiring accurate and stable outcomes. We demonstrate its potentialities in simulation studies and applications to concrete cases related to trade policies of major relevance for the European Union, such as circumvention of sanction by rerouting of trade flows.