2026/02/01 by Murad Farzulla · 1 voice
Economics, Econometrics and Finance · #q-fin.ST #q-fin.CP
arxiv published 2026/02/01 · arxiv updated 2026/07/11
Using the Crypto Fear & Greed Index and Bitcoin daily data, sentiment extremity predicts excess uncertainty beyond realized volatility. Extreme fear and extreme greed regimes exhibit significantly higher spreads than neutral periods -- the "extremity premium." Extended validation on the full Fear & Greed history (2018--2026, N = 2,896) confirms the finding: within-volatility-quintile comparisons show a premium (p < 0.001, pooled volatility-demeaned Cohen's d = 0.21 -- a post-hoc, exploratory test, as the pre-specified within-quintile endpoint does not survive multiple-testing correction; raw pooled extreme-vs-neutral d = 0.40), Granger causality runs from uncertainty to spreads (primary-sample F = 12.79; the extended-sample F = 211 is partly mechanical, sharing a high-low input with the spread measure), and placebo tests reject the null (p < 0.0001). The effect replicates on Ethereum and across 6 of 7 market cycles. However, the premium is sensitive to functional form: regression controls absorb regime effects, while nonparametric stratification preserves them. We interpret this as evidence that sentiment extremity captures volatility-regime interactions not fully represented by parametric controls -- consistent with, but not conclusively separable from, the F&G Index's embedded volatility component. An agent-based model is included as an illustrative device that reproduces the pattern qualitatively; because its spread-uncertainty link is coded rather than emergent, it does no inferential work (the reported moment-matching test validates a separate simplified model, not the full agent specification), and the inferential weight rests entirely on the empirical analysis. The results suggest that intensity, not direction, drives uncertainty-linked liquidity withdrawal in cryptocurrency markets, though identifying "pure" sentiment effects from volatility remains open.