Abstract
The problem of testing for the parametric form of the conditional variance is considered in a fully nonparametric regression model. A test statistic based on a weighted \(L_2\)-distance between the empirical characteristic functions of residuals constructed under the null hypothesis and under the alternative is proposed and studied theoretically. The null asymptotic distribution of the test statistic is obtained and employed to approximate the critical values. Finite sample properties of the proposed test are numerically investigated in several Monte Carlo experiments. The developed results assume independent data. Their extension to dependent observations is also discussed.
Similar content being viewed by others
References
Alba-Fernández, V., Jiménez-Gamero, M.D., Muñoz-García, J.: A test for the two-sample problem based on empirical characteristic functions. Comput. Stat. Data Anal. 52, 3730–3748 (2008)
Bradley, R.C.: Basic properties of strong mixing conditions. A survey and some open questions. Probab. Surv. 2, 107–144 (2005)
Dette, H., Hetzler, B.: A simple test for the parametric form of the variance function in nonparametric regression. Ann. Inst. Statist. Math. 61, 861–886 (2009a)
Dette, H., Hetzler, B.: Khmaladze transformation of integrated variance processes with applications to goodness-of-fit testing. Math. Methods Statist. 18, 97–116 (2009b)
Dette, H., Marchlewski, M.: A robust test for homoscedasticity in nonparametric regression. J. Nonparametr. Stat. 22, 723–736 (2010)
Dette, H., Neumeyer, N., Van Keilegom, I.: A new test for the parametric form of the variance function in non-parametric regression. J. R. Statist. Soc. Ser. B 69, 903–917 (2007)
Fan, J., Gijbels, I.: Local Polynomial Modelling and Its Applications. Champan & Hall, London (1996)
Fan, J., Yao, Q.: Nonlinear Time Series. Nonparametric and Parametric Methods. Springer, New York (2003)
Feller, W.: An Introduction to Probability Theory and Its Applications, vol. 2. Wiley, New Delhi (1971)
Hansen, B.E.: Uniform convergence rates for kernel estimation with dependent data. Econom. Theory 24, 726–748 (2008)
Hušková, M., Meintanis, S.G.: Goodness-of-fit tests for parametric regression models based on empirical characteristic functions. Kybernetika 45, 960–971 (2009)
Hušková, M., Meintanis, S.G.: Tests for the error distribution in nonparametric possibly heteroscedastic regression models. TEST 19, 92–112 (2010)
Koul, H.L., Song, W.: Conditional variance model checking. J. Stat. Plann. Inference 140, 1056–1072 (2010)
Liero, H.: Testing homoscedasticity in nonparametric regression. J. Nonparametr. Stat. 15, 31–51 (2003)
Neumeyer, N., Selk, L.: A note on non-parametric testing for Gaussian innovations in AR-ARCH models. J. Time Series Anal. 34, 362–367 (2013)
Neumeyer N, Van Keilegom I (2017) Bootstrap of residual processes in regression: to smooth or not to smooth? (available at arXiv:1712.02685v1)
Pardo-Fernández, J.C., Jiménez-Gamero, M.D., El Ghouch, A.: A nonparametric ANOVA-type test for regression curves based on characteristic functions. Scand. J. Stat. 42, 197–213 (2015a)
Pardo-Fernández, J.C., Jiménez-Gamero, M.D., El Ghouch, A.: Tests for the equality of conditional variance functions in nonparametric regression. Electron. J. Stat. 9, 1826–1851 (2015b)
Samarakoon, N., Song, W.: Minimum distance conditional variance function checking in heteroscedastic regression models. J. Multivariate Anal. 102, 579–600 (2011)
Samarakoon, N., Song, W.: Empirical smoothing lack-of-fit tests for variance function. J. Stat. Plann. Inference 142, 1128–1140 (2012)
Selk, L., Neumeyer, N.: Testing for a change of the innovation distribution in nonparametric autoregression: the sequential empirical process approach. Scand. J. Stat. 40, 770–788 (2013)
Wang, L., Zhou, X.-H.: Assessing the adequacy of variance function in heteroscedastic regression models. Biometrics 63, 1218–1225 (2007)
Wu, C.F.: Asymptotic theory of nonlinear least squares estimation. Ann. Stat. 9, 501–513 (1981)
Yoshihara, K.I.: Limiting behavior of U-statistics for stationary, absolutely regular processes. Z. Wahrsch. Verw. Gebiete 35, 237–252 (1976)
Yuan, K.H.: A theorem on uniform convergence of stochastic functions with applications. J. Multivariate Anal. 62, 100–109 (1997)
Acknowledgements
The authors thank the anonymous referees for their valuable time and careful comments, which improved the presentation of this paper. The authors acknowledge financial support from Grants MTM2014-55966-P and MTM2017-89422-P, funded by the Spanish Ministerio de Economía, Industria y Competitividad, the Agencia Estatal de Investigación and the European Regional Development Fund. J.C. Pardo-Fernández also acknowledges funding from Banco Santander and Complutense University of Madrid (Project PR26/16-5B-1). M. D. Jiménez-Gamero also acknowledges support from CRoNoS COST Action IC1408.
Author information
Authors and Affiliations
Corresponding author
A Proofs
A Proofs
1.1 A.1 Sketch of the proofs of results in Sect. 3
Observe that under Assumptions A.1, A.2 and A.3 for \((X_1,Y_1), \ldots , (X_n,Y_n)\) independent from (1), (see, for example, Hansen 2008),
Proof of (7) Let \(S_n(\theta )\) and \(S(\theta )\) be as defined in (3) and (5), respectively. From (13) and the SLLN, it follows that
Next we prove that the above convergence holds uniformly in \(\theta \). Routine calculations show that the derivative
is bounded (in probability) \(\forall \theta \in \Theta _0\), which implies that the family \(\left\{ S_n(\theta )-S(\theta ), \, \theta \in \right. \left. \Theta _0\right\} \) is equicontinuous. By the lemma in Yuan (1997), it follows that
Now the result follows from Assumption B.1 and Lemma 1 in Wu (1981). \(\square \)
Proof of (8) Under the assumptions made, routine calculations show that under \(H_0\),
By Taylor expansion,
Taking into account that \(\frac{\partial }{\partial \theta } S_n(\hat{\theta })=0\), the result follows from (14)–(16). \(\square \)
Proof of Theorem 3
From Lemma 10 (i) in Pardo-Fernández et al. (2015b), it follows that
with
and \(\sup _t |R_{1k}(t)|=o_P(1)\), \(k=1,2\). As for \(\hat{\varphi }_0(t)\), since
we have that
with \(\sup _t |R_{1k}(t)|=o_P(1)\), \(k=3,4\). From Lemma 11 in Pardo-Fernández et al. (2015b),
with \(\Vert R_{15}\Vert _w=o_P(1)\). By Taylor expansion and (8),
with \(\Vert R_{16}\Vert _w=o_P(1)\) and
Routine calculations show that
with \(\Vert R_{17}\Vert _w=o_P(1)\). Therefore, the result follows. \(\square \)
Proof of Theorem 8
From Lemma 10 (i) in Pardo-Fernández et al. (2015b), it follows that
with \(\tilde{\varphi }(t)\) as defined in (17) and
As for \(\hat{\varphi }_0(t)\), since
and
by Taylor expansion, we get
with
The result follows from (18)–(21), by taking into account that \(\Vert \tilde{\varphi }-{\varphi }\Vert _w=o_P(1)\) and \(\Vert \tilde{\varphi }_0-{\varphi }_0\Vert _w=o_P(1)\). \(\square \)
Proof of Theorem 9
Under \(H_{1n}\),
By applying the results in Yuan (1997), we get that (13) also hold under \(H_{1n}\). Now, the result follows by proceeding similarly to the proof of Theorem 3. \(\square \)
1.2 A.2 Sketch of the proofs of results in Sect. 6
Under Assumptions A.2, A.3, C.1–C.4 and C.6 (see, for example, Hansen 2008),
Proof of Theorem 11
Proceeding as in the proof of Theorem 3, we obtain
with \(\sup _t |R_{k}(t)|=o_P(1)\), \(k=1,2\),
From (22),
where \(K_h(\cdot )=\frac{1}{h}K(\frac{\cdot }{h})\). By using this identity, we get that
with \(\sup _t |R_{3}(t)|=o_P(1)\) and
By applying Hoeffding decomposition and Lemma 2 in Yoshihara (1976), we get that
with \(\sup _t |R_{4}(t)|=o_P(1)\).
By Taylor expansion and following similar steps to those given for \(V_1(t)\), we obtain
with \(\sup _t |R_{5}(t)|=o_P(1)\). Putting together all above facts, the result follows. \(\square \)
Rights and permissions
About this article
Cite this article
Pardo-Fernández, J.C., Jiménez-Gamero, M.D. A model specification test for the variance function in nonparametric regression. AStA Adv Stat Anal 103, 387–410 (2019). https://doi.org/10.1007/s10182-018-00336-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10182-018-00336-y