The Vector Autoregression (VAR) model analysis reveals key interactions between blob gas base fees and priority fees. The model's fit is indicated by a high log likelihood value of -2,335,520. Important diagnostic statistics, including AIC, BIC, and HQIC, suggest a well-performing model. Significant coefficients demonstrate strong persistence in blob gas base fees, while interactions with priority fees exhibit diminishing impact over time. Notably, increases in base fees slightly decrease priority fees, highlighting the complex dynamics in the network's pricing structure.
Table 14 displays the VAR model's key statistics. The log likelihood value is notably large at -2,335,520, suggesting the model's fit to the data under analysis.
The model shows strong persistence in datagas_base_fee, as indicated by the significant coefficient of 0.9588 for its first lag, and an effect of prior priority fees on current base fees.
Collection
[
|
...
]