Interpreting Causal Decomposition applied to Climate Phenomena

Abstract

Causal Decomposition (CD) is a novel technique which establishes causality levels between time series. CD bases on the Empirical Mode Decomposition (EMD). In this presentation, CD is applied to establish causality relationships after a preliminary analysis with tools derived from the Continuous Wavelet Transform. The studied series stem from climate phenomena: el Niño-Southern Oscillation (ENSO) and precipitations in Buenos Aires (Argentina) and Junín (Buenos Aires, Argentina). As expected, ENSO is a driver of the precipitation series. However, causality relations are also found between the precipitation series, which deserve a careful interpretation. This difficulty is part of an ongoing debate about the interpretation of CD.