Maximum Likelihood Estimation of Continuous-time Diffusion Models for Exchange Rates

被引：0

作者：

Choi, Seungmoon ^{[1
]}

Lee, Jaebum ^{[1
]}

机构：

[1] Univ Seoul, Sch Econ, Seoul, South Korea

来源：

EAST ASIAN ECONOMIC REVIEW | 2020年 / 24卷 / 01期

基金：

新加坡国家研究基金会;

关键词：

Foreign Exchange Rate; Diffusion Model; Maximum Likelihood Estimation; US Dollar; Euro; British Pound; Japanese Yen; DISCRETELY SAMPLED DIFFUSIONS; STOCHASTIC VOLATILITY; APPROXIMATION; EXPANSIONS; OPTIONS;

D O I：

10.11644/KIEP.EAER.2020.24.1.372

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

Five diffusion models are estimated using three different foreign exchange rates to find an appropriate model for each. Daily spot exchange rates expressed as the prices of 1 euro, 1 British pound and 100 Japanese yen in US dollars, respectively denoted by USD/EUR, USD/GBP, and USD/100JPY, are used. The maximum likelihood estimation method is implemented after deriving an approximate log-transition density function (log-TDF) of the diffusion processes because the true log-TDF is unknown. Of the five models, the most general model is the best fit for the USD/GBP, and USD/100JPY exchange rates, but it is not the case for the case of USD/EUR. Although we could not find any evidence of the mean-reverting property for the USD/EUR exchange rate, the USD/GBP, and USD/100JPY exchange rates show the mean-reversion behavior. Interestingly, the volatility function of the USD/EUR exchange rate is increasing in the exchange rate while the volatility functions of the USD/GBP and USD/100Yen exchange rates have a U-shape. Our results reveal that more care has to be taken when determining a diffusion model for the exchange rate. The results also imply that we may have to use a more general diffusion model than those proposed in the literature when developing economic theories for the behavior of the exchange rate and pricing foreign currency options or derivatives.

引用

页码：61 / 87

页数：27

共 50 条

[21] Adaptive testing in continuous-time diffusion models
Gao, JT
King, M
ECONOMETRIC THEORY, 2004, 20 (05) : 844 - 882
[22] Maximum likelihood parameter estimation from incomplete data via the sensitivity equations: The continuous-time case
Charalambous, CD
Logothetis, A
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2000, 45 (05) : 928 - 934
[23] Maximum Likelihood Identification of a Continuous-Time Oscillator Utilizing Sampled Data
Gonzalez, Karen
Coronel, Maria
Carvajal, Rodrigo
Escarate, Pedro
Aguero, Juan C.
IFAC PAPERSONLINE, 2018, 51 (15): : 712 - 717
[24] Maximum likelihood estimation in space time bilinear models
Dai, YQ
Billard, L
JOURNAL OF TIME SERIES ANALYSIS, 2003, 24 (01) : 25 - 44
[25] On Bayesian Inference for Continuous-time Autoregressive Models without Likelihood
Ji, Chunlin
Yang, Ligong
Zhu, Wanchuang
Liu, Yiqi
Deng, Ke
2018 21ST INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2018, : 2137 - 2142
[26] Influence Estimation and Maximization in Continuous-Time Diffusion Networks
Gomez-Rodriguez, Manuel
Song, Le
Du, Nan
Zha, Hongyuan
Schoelkopf, Bernhard
ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2016, 34 (02)
[27] Maximum likelihood estimation of diffusions by continuous time Markov chain
Kirkby, J. L.
Nguyen, Dang H.
Nguyen, Duy
Nguyen, Nhu N.
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2022, 168
[28] Exact finite-dimensional filters for maximum likelihood parameter estimation of continuous-time linear Gaussian systems
Elliott, RJ
Krishnamurthy, V
SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1997, 35 (06) : 1908 - 1923
[29] On continuous-time models of term structure of interest rates
Rutkowski, M
STOCHASTIC PROCESSES AND RELATED TOPICS, 1996, 10 : 139 - 152
[30] Maximum likelihood estimator for hidden Markov models in continuous time
Chigansky P.
Statistical Inference for Stochastic Processes, 2009, 12 (2) : 139 - 163

← 1 2 3 4 5 →