prikaz prve stranice dokumenta Identifikacija cjenovnih skokova pomoću visokofrekventnih podataka
  Download
PDF 1.98 MB
master's thesis
Identifikacija cjenovnih skokova pomoću visokofrekventnih podataka
Zagreb: University of Zagreb, Faculty of Economics and Business, 2022. urn:nbn:hr:148:114151
Stürmer, Marcela
University of Zagreb
Faculty of Economics and Business
Department of Managerial Economics

Institutional repository: REPEFZG

Cite this document

Stürmer, M. (2022). Identifikacija cjenovnih skokova pomoću visokofrekventnih podataka (Master's thesis). Zagreb: University of Zagreb, Faculty of Economics and Business. Retrieved from https://urn.nsk.hr/urn:nbn:hr:148:114151

Stürmer, Marcela. "Identifikacija cjenovnih skokova pomoću visokofrekventnih podataka." Master's thesis, University of Zagreb, Faculty of Economics and Business, 2022. https://urn.nsk.hr/urn:nbn:hr:148:114151

Stürmer, Marcela. "Identifikacija cjenovnih skokova pomoću visokofrekventnih podataka." Master's thesis, University of Zagreb, Faculty of Economics and Business, 2022. https://urn.nsk.hr/urn:nbn:hr:148:114151

Stürmer, M. (2022). 'Identifikacija cjenovnih skokova pomoću visokofrekventnih podataka', Master's thesis, University of Zagreb, Faculty of Economics and Business, accessed 17 August 2024, https://urn.nsk.hr/urn:nbn:hr:148:114151

Stürmer M. Identifikacija cjenovnih skokova pomoću visokofrekventnih podataka [Master's thesis]. Zagreb: University of Zagreb, Faculty of Economics and Business; 2022 [cited 2024 August 17] Available at: https://urn.nsk.hr/urn:nbn:hr:148:114151

M. Stürmer, "Identifikacija cjenovnih skokova pomoću visokofrekventnih podataka", Master's thesis, University of Zagreb, Faculty of Economics and Business, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:148:114151

Metadata
TitleIdentifikacija cjenovnih skokova pomoću visokofrekventnih podataka
Title (english)Price jumps identification using high-frequency data
AuthorMarcela Stürmer
MentorJosip Arnerić (mentor)
MBZ: 274256
Committee memberDenis Dolinar (predsjednik povjerenstva)
Committee memberDavor Zoričić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Economics and Business
(Department of Managerial Economics)
Zagreb
Defense date and country2022-03-30, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Economics
Business Mathematics and Statistics
Abstract
Iako je osnovna pretpostavka modela vrednovanja financijske imovine kontinuiranost cijena, koje slijede određeni stohastički proces s kontinuiranim prostorom stanja i kontinuiranim vremenom, u praksi su cijene na financijskim tržištima opažene u diskretnim vremenskim intervalima. Tehnološki napredak i sve veća dostupnost visokofrekventnih podataka, opaženih u jako kratkim intervalima vremena, primjerice svake minute ili sekunde, omogućili su upotrebu potpunijih informacija za procjenu kontinuiranog dijela procesa cijena koji najčešće prati Brownovo gibanje, kao i dijela procesa cjenovnih skokova koji se kao aditivni član pridružuje Brownovom gibanju. Pri tome se proces cjenovnih skokova opisuje Poissonovim stohastičkim procesom s diskretnom prostorom stanja, ali kontinuiranim vremenom. Pridruživanje procesa cjenovnih skokova stohastičkom procesu cijena bitno mijenja tradicionalno shvaćanje modela vrednovanja financijske imovine te ima ozbiljne posljedice za upravljanje financijskim rizikom i određivanje cijena, a novija literatura nudi empirijske dokaze ove tvrdnje. Kako bi se cjenovni skokovi mogli identificirati koristeći visokofrekventne podatke, razvijene su različite metode koje se primarno temelje na usporedbi procjenitelja realizirane varijance prinosa financijske imovine koji su robusni i onih koji nisu robusni na cjenovne skokove. Svrha ovoga rada je dati teoretski uvid u određivanje cjenovnih skokova, njihove uzroke i posljedice, obrazložiti statističke testove za njihovu identifikaciju, specificirati cjenovne skokove na visokofrekventnim podacima za hrvatsko dioničko tržište te istražiti njihov utjecaj na volumen trgovanja.
Abstract (english)
Although the basic assumption of the financial asset valuation model is price continuity, where price follows a certain stochastic process with a continuous state space and continuous time, in practice, prices in financial markets are observed at discrete time intervals. Technological advances and increasing availability of high-frequency data, observed at very short intervals, e.g. every minute or second, have made it possible to use more complete information to estimate the continuous part of the price process that follows Brownian motion and a part of the jump process that joins as an additive member to Brownian motion. The process of price jumps is described by Poisson's stochastic process with discrete state space but continuous time. Joining the price jump process to the stochastic price process significantly changes traditional understanding of the financial asset valuation model and has serious consequences for financial risk management and pricing, and recent literature offers empirical evidence for this claim. In order to be able to identify price jumps using high-frequency dana, various methods have been developed that are primarily based on comparing estimators of realized variance of financial asset returns that are robust and those that are not robust to price jumps. The purpose of this paper is to provide theoretical insight into determining price jumps, their causes and consequences, to explain statistical tests for their identification, to specify price jumps on high-frequency data for the Croatian stock market and to investigate their impact on trading volume.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:148:114151
Study programmeTitle: Business Economics
Study programme type: university
Study level: integrated undergraduate and graduate
Academic / professional title: magistar/magistra ekonomije (magistar/magistra ekonomije)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0) icon
Created on2022-04-04 14:56:59