Working Paper: NBER ID: w18078
Authors: Fei Chen; Francis X. Diebold; Frank Schorfheide
Abstract: We propose and illustrate a Markov-switching multi-fractal duration (MSMD) model for analysis of inter-trade durations in financial markets. We establish several of its key properties with emphasis on high persistence (indeed long memory). Empirical exploration suggests MSMD's superiority relative to leading competitors.
Keywords: Markov-Switching; Multifractal; Intertrade Durations; Financial Econometrics
JEL Codes: C22; C41
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| MSMD model structure (C30) | observed duration dynamics (C41) |
| MSMD model captures high persistence (C22) | improvement over ACD model (C22) |
| MSMD model incorporates long memory (C22) | covariance stationarity (C22) |
| MSMD model captures overdispersion (C52) | standard deviation exceeds mean (C46) |
| MSMD model's intensity components driven by Markov-switching process (C22) | varying degrees of persistence in durations (C41) |
| MSMD model structure and dynamics (C69) | accuracy of intertrade duration predictions (C41) |