Key points are not available for this paper at this time.
Drawing from the big data archive of Google Trends, we innovatively construct a novel data set, the composite news-based speculation index, to proxy for the role of speculation in the predictability of carbon prices. We employ a theory-based multi-factor predictive framework to test the hypothesis that both emission compliance and emission noncompliance dynamics of the ETS matter in the predictability of carbon prices. We show that speculation is a good predictor of carbon prices. We find the robustness of the forecasting power of speculation in the predictability of carbon prices evident for both in-sample and out-of-sample forecasts and across different forecast horizons.
Isah et al. (Tue,) studied this question.