Spectral Density Based Goodness‐of‐Fit Tests for Time Series Models

By Efstathios Paparoditis. 2000

89 citations recorded by the source corpus.

Subfields: Finance, Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/392b003de59191b4f90448164375907b6f93fcd6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Finance

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Generalized spectral tests for the martingale difference hypothesis (2006, methodology): “On the other hand, indicator functions have been used in Stute (1997), Koul and Stute (1999), Park and Whang (1999), Whang (2000) or Domı́nguez and Lobato (2003).”
Nonparametric inference with generalized likelihood ratio tests (2007, methodology): “For example, the testing procedure in Paparoditis (2000) using the Priestley-Chao estimator and an L2-distance, the testing approach without smoothing, as with Dzhaparidze’s (1986, p. 273) test statistic based on a cumulative rescaled spectral density, and the Kolmogorov-Smirnov and Cramér-von…”
TESTING FOR WHITE NOISE UNDER UNKNOWN DEPENDENCE AND ITS APPLICATIONS TO DIAGNOSTIC CHECKING FOR TIME SERIES MODELS (2010, methodology): “Tests developed by Hong (1996), Paparoditis (2000), and Chen and Deo (2004a) are of the first type, and they usually involve a smoothing parameter and have trivial power against n−1/2 local alternatives.”
Testing nonparametric and semiparametric hypotheses in vector stationary processes (2008, background): “For details, we refer to Hong [39,40], who obtained similar results as in Theorems 5.1 and 5.4 in the special case of tests for serial correlation and tests for noncorrelation; see also Paparoditis [50] for the case of goodness-of-fit tests.”
Goodness-of-Fit Tests for Linear and Nonlinear Time Series Models (2006, methodology): “In particular, classical Portmanteau tests are based on checking the serial uncorrelatedness of the errors {et(θ0)} (see, e.g., Box and Pierce 1970; Ljung and Box 1978; Paparoditis 2000; Delgado, Hidalgo, and Velasco 2003).”
An updated review of Goodness-of-Fit tests for regression models (2013, methodology): “For weakly dependent observations, Neumann and Paparoditis (2000) modified Tn including a parametric estimate of the stationary density, using bootstrap for calibration.”
Power transformations to induce normality and their applications (2004, background): “…2 .λj/, .19/ where f̂ .λ/ = 2π n n−1∑ j=1 W.λ − λj/ Ix.λj/ f.λj/ , f.·/ is the spectral density of the fitted model and Ix.λ/= .2πn/−1|Σnt=1xt exp.−itλ/|2 is the periodogram of the observations xt: Another frequency domain test statistic, similar in spirit to Tn, was studied by Paparoditis (2000).”
Validating Stationarity Assumptions in Time Series Analysis by Rolling Local Periodograms (2010, unknown): “By lemma 3 of Papar- oditis (2000), it follows that N √ b ∑M r=1 ar(Qn, (ur) − μn) ⇒ N(0, τ 2 ∑M r=1 a2r ).”
Multi-scale tests for serial correlation (2015, background): “Paparoditis (2000) proposes a test statistic based on the distance between a kernel estimator of the ratio between the true and the hypothesized spectral density and the expected value of the estimator under the null.”