Bootstrap inference in autoregressive duration models
arXiv:2607.28294
The paper proposes bootstrap methods for inference in autoregressive conditional duration (ACD) models with random sample sizes, showing consistency under different tail-index conditions and applying the approach to cryptocurrency ETF transaction data.
Abstract
This paper develops bootstrap inference for autoregressive conditional duration (ACD) models observed over a fixed calendar span, so that the number of durations is random. We study recursive schemes that either fix the calendar span or the realized event count. For the fixed-count bootstrap, we establish consistency when the duration tail index satisfies . When , classical consistency fails because the estimator has a mixed-normal limit, but the bootstrap reproduces its conditional Gaussian component. Consequently, basic percentile intervals remain first-order valid and bootstrap -statistics are asymptotically standard normal. Monte Carlo experiments show accurate finite-sample inference across finite- and infinite-mean regimes and robustness to non-exponential innovations. An application to cryptocurrency ETF transaction durations finds strong persistence and illustrates the practical difference between fixed-count and random-count inference.