Using Stablecoin Lending Metrics to Study Ethereum Volatility

Summary

This report studies whether DeFi lending activity in USDC, USDT, and DAI is associated with Ethereum volatility. It estimates daily volatility with the Garman-Klass method, which uses open, high, low, and close prices, then applies Augmented Dickey-Fuller tests and first differences to address non-stationary series before calculating correlations.

Across the reported results, repayment counts have positive correlations with ETH volatility in all three stablecoin ecosystems, while some withdrawal and borrowing measures also show positive associations. The report presents these correlations as possible indicators of market stress and liquidity adjustment. These are associations, not proof that lending activity predicts or causes volatility; the provided text does not show a forecasting test or out-of-sample validation. It also mentions multicollinearity and variable selection, but that section is incomplete, limiting assessment of how candidate metrics were ultimately handled.

Key ideas

• The analysis estimates ETH volatility from OHLC data using the Garman-Klass approach.
• ADF testing identifies non-stationary series, which the report transforms using first differences.
• Repayment counts show positive correlations with ETH volatility across USDC, USDT, and DAI.
• Correlations suggest possible indicators of market stress but do not establish causation or forecasting value.
• The multicollinearity and selection discussion is incomplete in the available text.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.