Estimation under copula-based Markov normal mixture models for serially correlated data

Wei Cheng Lin, Takeshi Emura, Li Hsien Sun

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

We propose an estimation method under a copula-based Markov model for serially correlated data. Motivated by the fat-tailed distribution of financial assets, we select a normal mixture distribution for the marginal distribution. Based on the normal mixture distribution for the marginal distribution and the Clayton copula for serial dependence, we obtain the corresponding likelihood function. In order to obtain the maximum likelihood estimators, we apply the Newton-Raphson algorithm with appropriate transformations and initial values. We conduct simulation studies to evaluate the performance of the proposed method. In the empirical analysis, the stock price of Dow Jones Industrial Average is analyzed for illustration.

Original languageEnglish
Pages (from-to)4483-4515
Number of pages33
JournalCommunications in Statistics - Simulation and Computation
Volume50
Issue number12
DOIs
StatePublished - 2021

Keywords

  • Copula
  • Log return
  • Markov model
  • Newton-Raphson algorithm
  • Normal mixture distribution

Fingerprint

Dive into the research topics of 'Estimation under copula-based Markov normal mixture models for serially correlated data'. Together they form a unique fingerprint.

Cite this