Diagnostic checking integer-valued ARCH(p) models using conditional residual autocorrelations

Time series of counts are commonly observed in real-world applications. The integer-valued ARCH(p) models are able to describe integer-valued processes and offer the potential to be widely applied in practice in future. This paper develops an asymptotic theory for (partial) autocorrelations of the conditional residuals from the integer-valued ARCH(p) model. Based on the above results, we propose five portmanteau test statistics, which are very useful in checking the adequacy of a fitted integer-valued ARCH specification. The asymptotic distributions of the statistics are derived and their finite sample properties are studied in detail through Monte Carlo simulations. Finally, we illustrate the results analyzing two empirical examples.

[1]  G. Box,et al.  On a measure of lack of fit in time series models , 1978 .

[2]  Fred L. Ramsey,et al.  Characterization of the Partial Autocorrelation Function , 1974 .

[3]  Esther Ruiz,et al.  A powerful test for conditional heteroscedasticity for financial time series with highly persistent volatilities , 2003 .

[4]  Rohit S. Deo,et al.  Power transformations to induce normality and their applications , 2004 .

[5]  Wai Keung Li,et al.  Diagnostic Checks in Time Series , 2003 .

[6]  A. I. McLeod,et al.  DIAGNOSTIC CHECKING ARMA TIME SERIES MODELS USING SQUARED‐RESIDUAL AUTOCORRELATIONS , 1983 .

[7]  Julio Rodríguez,et al.  The log of the determinant of the autocorrelation matrix for testing goodness of fit in time series , 2006 .

[8]  Julio Rodríguez,et al.  A Powerful Portmanteau Test of Lack of Fit for Time Series , 2002 .

[9]  Alain Latour,et al.  Integer‐Valued GARCH Process , 2006 .

[10]  Christian H. Weiß,et al.  Thinning operations for modeling time series of counts—a survey , 2008 .

[11]  A. Ian McLeod,et al.  Improved Pena-Rodriguez portmanteau test , 2006, Comput. Stat. Data Anal..

[12]  W. Li,et al.  On the squared residual autocorrelations in non-linear time series with conditional heteroskedasticity , 1994 .

[13]  P. Kokoszka,et al.  ASYMPTOTICS FOR GARCH SQUARED RESIDUAL CORRELATIONS , 2003, Econometric Theory.

[14]  W. Stout.  Almost sure convergence , 1974 .

[15]  J. Wellner,et al.  Empirical Processes with Applications to Statistics , 2009 .

[16]  Christian H. Weiß,et al.  Modelling time series of counts with overdispersion , 2009, Stat. Methods Appl..

[17]  G. Box.  Some Theorems on Quadratic Forms Applied in the Study of Analysis of Variance Problems, I. Effect of Inequality of Variance in the One-Way Classification , 1954 .

[18]  Fukang Zhu,et al.  Estimation and testing for a Poisson autoregressive model , 2011 .

[19]  F. E. Satterthwaite.  Synthesis of variance , 1941 .

[20]  J. P. BfflOF.  Computing the distribution of quadratic forms in normal variables , 2005 .

[21]  Wai Keung Li,et al.  On Fractionally Integrated Autoregressive Moving-Average Time Series Models with Conditional Heteroscedasticity , 1997 .

[22]  Anna Clara Monti.  A proposal for a residual autocorrelation test in linear models , 1994 .

[23]  P. Billingsley,et al.  Convergence of Probability Measures , 1969 .

[24]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[25]  Piotr Kokoszka,et al.  LARGE SAMPLE DISTRIBUTION OF WEIGHTED SUMS OF ARCH(p) SQUARED RESIDUAL CORRELATIONS , 2001, Econometric Theory.