Nonlinear dynamics of daily cash prices

Seung Ryong Yang, B. Wade Brorsen

Research output: Contribution to journalArticle

47 Citations (Scopus)

Abstract

Daily cash price changes are not normally distributed. Their empirical distributions have fat tails and most are skewed. In addition, they are not independent. Among the diffusion-jump, extended generalized autoregressive conditional heteroskedasticity (GARCH), and deterministic chaos processes, a GARCH process with residuals following a student distribution is the most likely. Our GARCH model reduces leptokurtosis, removes nonlinear dependence, and provides a considerable improvement over the i.i.d. normal model. The GARCH process is not well calibrated because it cannot explain all the observed nonnormality, but it does yield asymptotically valid hypothesis tests.

Original languageEnglish
Pages (from-to)706-715
Number of pages10
JournalAmerican Journal of Agricultural Economics
Volume74
Issue number3
DOIs
Publication statusPublished - 1992
Externally publishedYes

Fingerprint

heteroskedasticity
Nonlinear Dynamics
Fats
Students
students
tail
Cash
Autoregressive conditional heteroskedasticity
Nonlinear dynamics
lipids
testing

Keywords

  • Conditional heteroskedasticity
  • Deterministic chaos
  • Diffusion-jump
  • Leptokurtosis
  • Market anomalies
  • Skewness

ASJC Scopus subject areas

  • Agricultural and Biological Sciences (miscellaneous)
  • Economics and Econometrics

Cite this

Nonlinear dynamics of daily cash prices. / Yang, Seung Ryong; Brorsen, B. Wade.

In: American Journal of Agricultural Economics, Vol. 74, No. 3, 1992, p. 706-715.

Research output: Contribution to journalArticle

Yang, Seung Ryong ; Brorsen, B. Wade. / Nonlinear dynamics of daily cash prices. In: American Journal of Agricultural Economics. 1992 ; Vol. 74, No. 3. pp. 706-715.
@article{9597b2e6cdaf4f52960069a053f88b71,
title = "Nonlinear dynamics of daily cash prices",
abstract = "Daily cash price changes are not normally distributed. Their empirical distributions have fat tails and most are skewed. In addition, they are not independent. Among the diffusion-jump, extended generalized autoregressive conditional heteroskedasticity (GARCH), and deterministic chaos processes, a GARCH process with residuals following a student distribution is the most likely. Our GARCH model reduces leptokurtosis, removes nonlinear dependence, and provides a considerable improvement over the i.i.d. normal model. The GARCH process is not well calibrated because it cannot explain all the observed nonnormality, but it does yield asymptotically valid hypothesis tests.",
keywords = "Conditional heteroskedasticity, Deterministic chaos, Diffusion-jump, Leptokurtosis, Market anomalies, Skewness",
author = "Yang, {Seung Ryong} and Brorsen, {B. Wade}",
year = "1992",
doi = "10.2307/1242584",
language = "English",
volume = "74",
pages = "706--715",
journal = "American Journal of Agricultural Economics",
issn = "0002-9092",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - Nonlinear dynamics of daily cash prices

AU - Yang, Seung Ryong

AU - Brorsen, B. Wade

PY - 1992

Y1 - 1992

N2 - Daily cash price changes are not normally distributed. Their empirical distributions have fat tails and most are skewed. In addition, they are not independent. Among the diffusion-jump, extended generalized autoregressive conditional heteroskedasticity (GARCH), and deterministic chaos processes, a GARCH process with residuals following a student distribution is the most likely. Our GARCH model reduces leptokurtosis, removes nonlinear dependence, and provides a considerable improvement over the i.i.d. normal model. The GARCH process is not well calibrated because it cannot explain all the observed nonnormality, but it does yield asymptotically valid hypothesis tests.

AB - Daily cash price changes are not normally distributed. Their empirical distributions have fat tails and most are skewed. In addition, they are not independent. Among the diffusion-jump, extended generalized autoregressive conditional heteroskedasticity (GARCH), and deterministic chaos processes, a GARCH process with residuals following a student distribution is the most likely. Our GARCH model reduces leptokurtosis, removes nonlinear dependence, and provides a considerable improvement over the i.i.d. normal model. The GARCH process is not well calibrated because it cannot explain all the observed nonnormality, but it does yield asymptotically valid hypothesis tests.

KW - Conditional heteroskedasticity

KW - Deterministic chaos

KW - Diffusion-jump

KW - Leptokurtosis

KW - Market anomalies

KW - Skewness

UR - http://www.scopus.com/inward/record.url?scp=0004035488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0004035488&partnerID=8YFLogxK

U2 - 10.2307/1242584

DO - 10.2307/1242584

M3 - Article

AN - SCOPUS:0004035488

VL - 74

SP - 706

EP - 715

JO - American Journal of Agricultural Economics

JF - American Journal of Agricultural Economics

SN - 0002-9092

IS - 3

ER -