Filtering on a partially observed ultra-high-frequency data model (Q2501130)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Filtering on a partially observed ultra-high-frequency data model |
scientific article; zbMATH DE number 5051228
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Filtering on a partially observed ultra-high-frequency data model |
scientific article; zbMATH DE number 5051228 |
Statements
Filtering on a partially observed ultra-high-frequency data model (English)
0 references
4 September 2006
0 references
A model for intraday stock price movements is considered. The jump-intensity of the logreturn process is a function of the whole history of a hidden marked point process. The aim is to find the conditional law of such intensity given the history of the logreturn process. Under a Markovianity assumption, related with the weak form of market efficiency, classical filtering techniques are used. The law of the jump-intensity, given the history of the logreturn price, is evaluated and a discussion on a particular case is performed.
0 references
financial markets
0 references
ultra-high-frequency data
0 references
stochastic model
0 references
nonlinear filtering
0 references
Markov jumping processes
0 references
0 references
0 references
0.9256395
0 references
0.8887348
0 references
0.85922706
0 references
0 references
0.8535788
0 references
0.8532647
0 references
0.8529008
0 references
0.8494922
0 references
