Fitting non-Gaussian persistent data. (English) Zbl 1306.62202

Summary: This paper discusses a new methodology for modeling non-Gaussian time series with long-range dependence. The class of models proposed admits continuous or discrete data and considers the conditional variance as a function of the conditional mean. These types of models are motivated by empirical properties exhibited by some time series. The proposed methodology is illustrated with the analysis of two real-life persistent time series. The first application is concerned with the modeling of stock market daily trading volumes, whereas the second application consists of a study of mineral deposit measurements.


62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62P05 Applications of statistics to actuarial sciences and financial mathematics
91B84 Economic time series analysis
62P12 Applications of statistics to environmental and related topics
86A32 Geostatistics
Full Text: DOI Link


[1] Palma, Long-memory Time Series: Theory and Methods (2007) · Zbl 1183.62153
[2] Lobato, Long-memory in stock-market trading volume, Journal of Business and Economic Statistics 18 pp 410– (2000)
[3] Advances in Geophysics, in: Long-Range Persistence in Geophysical Time Series (1999)
[4] Shumway, Time Series Analysis and Its Applications (2000) · Zbl 0942.62098
[5] Brockwell, Likelihood-based analysis of a class of generalized long-memory time series models, Journal of Time Series Analysis 28 pp 386– (2006) · Zbl 1164.62376
[6] Andersen, Return volatility and trading volume: an information flow interpretation of stochastic volatility, Journal of Finance 60 pp 169– (1996)
[7] Stanislavsky, FARIMA modeling of solar flare activity from empirical time series of soft x-ray solar emission, The Astrophysical Journal 693 pp 1877– (2009)
[8] Samorodnitsky, Stable Non-Gaussian Random Processes (1994)
[9] Chechkin, A model for persistent Levy motion, Physica A: Statistical Mechanics and Its Applications 277 pp 312– (2000)
[10] Granger, An introduction to long-range time series models and fractional differencing, Journal of Time Series Analysis 1 pp 15– (1980) · Zbl 0503.62079
[11] Hosking, Fractional differencing, Biometrika 68 pp 165– (1981) · Zbl 0464.62088
[12] Grunwald, Non-Gaussian conditional linear AR(1) models, The Australian & New Zealand Journal of Statistics 42 pp 479– (2000) · Zbl 1018.62065
[13] Brockwell, Time Series Theory and Methods (1991) · Zbl 0709.62080
[14] Box, Time Series Analysis (1994)
[15] Press, Numerical Recipes. The Art of Scientific Computing (1992)
[16] Taniguchi, Asymptotic Theory of Statistical Inference for Time Series (2000) · Zbl 0955.62088
[17] Hosoya, Limit theory with long-range dependence and statistical inference of related models, Annals of Statistics 25 pp 105– (1997) · Zbl 0873.62096
[18] Ling, On fractionally integrated autoregressive time series models with conditionally heteroscesdaticity, Journal of the American Statistical Association 92 pp 1184– (1997) · Zbl 1067.62572
[19] Li, A survey of recent theoretical results for time series models with GARCH errors, Journal of Economic Survey 16 pp 245– (2002)
[20] Tsay, Analysis of Financial Time Series (2002)
[21] Baillie, Estimation of GARCH models from the autocorrelations of the squares of a process, Journal of Time Series Analysis 22 pp 631– (2001) · Zbl 0984.62063
[22] Escanciano, An automatic Portmanteau test for serial correlation, Journal of Econometrics 151 pp 140– (2009) · Zbl 1431.62365
[23] Chan, State-space modeling of long-memory processes, Annals of Statistics 26 pp 719– (1998) · Zbl 0929.62091
[24] Durrett, Probability: Theory and Examples (1996)
[25] Billingsley, Probability and Measure (1995)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.