Gaussian Quasi-maximum Likelihood Estimator Research Articles

Quasi-maximum Likelihood Inference for Linear Double Autoregressive Models

This paper investigates the quasi-maximum likelihood inference including estimation, model selection and diagnostic checking for linear double autoregressive (DAR) models, where all asymptotic properties are established under only fractional moment of the observed process. We propose a Gaussian quasi-maximum likelihood estimator (G-QMLE) and an exponential quasi-maximum likelihood estimator (E-QMLE) for the linear DAR model, and establish the consistency and asymptotic normality for both estimators. Based on the G-QMLE and E-QMLE, two Bayesian information criteria are proposed for model selection, and two mixed portmanteau tests are constructed to check the adequacy of fitted models. Moreover, we compare the proposed G-QMLE and E-QMLE with the existing doubly weighted quantile regression estimator in terms of the asymptotic efficiency and numerical performance. Simulation studies illustrate the finite-sample performance of the proposed inference tools, and a real example on the Bitcoin return series shows the usefulness of the proposed inference tools.

An improved FIGARCH model with the fractional differencing operator (1-νL)d

In this study, we propose a new volatility model called the product memory GARCH model by replacing (1 − L)d in the FIGARCH model of Baillie et al. (1996) with (1 − νL)d for 0 ≤ ν ≤ 1, where the impulse response function in its ARCH(∞) process has a decay rate in the form of the product of a geometric memory rate and a hyperbolic memory rate when the lags increase. Under the ARCH(∞) framework, the non-negativity constraints, the existence of the second, fourth, sixth, and eighth moments, and the memory length are investigated, and the Gaussian quasi-maximum likelihood estimation is also discussed. This improved model is of considerable significance in the evolution of GARCH-type models and financial econometrics.

Extended Glivenko–Cantelli theorem and L 1 strong consistency of innovation density estimator for time-varying semiparametric ARCH model

ABSTRACT This paper extends the classical Glivenko–Cantelli theorem for the empirical cumulative distribution function based on the innovations in the ARCH model with a slowly time-varying trend. In this semiparametric time-varying model, strong consistency for the innovation density estimator via kernel smoothing method is established, given that the trend and ARCH parameter estimators meet some mild conditions. Besides, the strong consistency for the Gaussian quasi maximum likelihood estimator (QMLE) in the time-varying ARCH parameter is established as well. Moreover, in terms of the existence of the trend in the data, two major nonparametric trend estimators, B-spline and kernel estimators, are shown to be appropriate for the strong consistency results.

Generalized Gaussian quasi-maximum likelihood estimation for most common time series

We propose a consistent estimator for the parameter shape of the generalized gaussian noise in the class of causal time series including ARMA, AR(∞), GARCH, ARCH(∞), ARMA-GARCH, APARCH, ARMA-APARCH,…, processes. As well we prove the consistency and the asymptotic normality of the Generalized Gaussian Quasi-Maximum Likelihood Estimator (GGQMLE) for this class of causal time series with any fixed parameter shape, which over-performs the efficiency of the classical Gaussian QMLE. Monte Carlo experiments confirm that the accuracy of the proposed estimators.

Epidemic change-point detection in general causal time series

We consider an epidemic change-point detection in a large class of causal time series models, including among other processes, AR(∞), ARCH(∞), TARCH(∞), ARMA-GARCH. A test statistic based on the Gaussian quasi-maximum likelihood estimator of the parameter is proposed. It is shown that, under the null hypothesis of no change, the test statistic converges to a distribution obtained from a difference of two Brownian bridge and diverges to infinity under the epidemic alternative. Numerical results for simulation and real data example are provided.

An indirect proof for the asymptotic properties of VARMA model estimators

Strong consistency and asymptotic normality of a Gaussian quasi-maximum likelihood estimator for the parameters of a causal, invertible, and identifiable vector autoregressive-moving average (VARMA) model are established in an indirect way. The proof is based on similar results for a much wider class of VARMA models with time-dependent coefficients, hence in the context of non-stationary and heteroscedastic time series. For that reason, the proof avoids spectral analysis arguments and does not make use of ergodicity. The results presented are also applicable to ARMA models.

QML estimation with non-summable weight matrices

This paper revisits the theory of asymptotic behaviour of the well-known Gaussian Quasi-Maximum Likelihood estimator of parameters in mixed regressive, high-order autoregressive spatial models. We generalise the approach previously published in the econometric literature by weakening the assumptions imposed on the spatial weight matrix. This allows consideration of interaction patterns with a potentially larger degree of spatial dependence. Moreover, we broaden the class of admissible distributions of model residuals. As an example application of our new asymptotic analysis we also consider the large sample behaviour of a general group effects design.

Non-standard inference for augmented double autoregressive models with null volatility coefficients

This paper considers an augmented double autoregressive (DAR) model, which allows null volatility coefficients to circumvent the over-parameterization problem in the DAR model. Since the volatility coefficients might be on the boundary, the statistical inference methods based on the Gaussian quasi-maximum likelihood estimation (GQMLE) become non-standard, and their asymptotics require the data to have a finite sixth moment, which narrows the applicable scope in studying heavy-tailed data. To overcome this deficiency, this paper develops a systematic statistical inference procedure based on the self-weighted GQMLE for the augmented DAR model. Except for the Lagrange multiplier test statistic, the Wald, quasi-likelihood ratio and portmanteau test statistics are all shown to have non-standard asymptotics. The entire procedure is valid as long as the data are stationary, and its usefulness is illustrated by simulation studies and one real example.

The Threshold GARCH Model: Estimation and Density Forecasting for Financial Returns*

AbstractWe consider multiple threshold value-at-risk (VaRt) estimation and density forecasting for financial data following a threshold GARCH model. We develop an α-quantile quasi-maximum likelihood estimation (QMLE) method for VaRt by showing that the associated density function is an α-quantile density and belongs to the tick-exponential family. This establishes that our estimator is consistent for the parameters of VaRt. We propose a density forecasting method for quantile models based on VaRt at a single nonextreme level, which overcomes some limitations of existing forecasting methods with quantile models. We find that for heavy-tailed financial data our α-quantile QMLE method for VaRt outperforms the Gaussian QMLE method for volatility. We also find that density forecasts based on VaRt outperform those based on the volatility of financial data. Empirical work on market returns shows that our approach also outperforms some benchmark models for density forecasting of financial returns.

Non-Gaussian quasi-likelihood estimation of SDE driven by locally stable Lévy process

We address estimation of parametric coefficients of a pure-jump Lévy driven univariate stochastic differential equation (SDE) model, which is observed at high frequency over a fixed time period. It is known from the previous study (Masuda, 2013) that adopting the conventional Gaussian quasi-maximum likelihood estimator then leads to an inconsistent estimator. In this paper, under the assumption that the driving Lévy process is locally stable, we extend the Gaussian framework into a non-Gaussian counterpart, by introducing a novel quasi-likelihood function formally based on the small-time stable approximation of the unknown transition density. The resulting estimator turns out to be asymptotically mixed normally distributed without ergodicity and finite moments for a wide range of the driving pure-jump Lévy processes, showing much better theoretical performance compared with the Gaussian quasi-maximum likelihood estimator. Extensive simulations are carried out to show good estimation accuracy. The case of large-time asymptotics under ergodicity is briefly mentioned as well, where we can deduce an analogous asymptotic normality result.

QML INFERENCE FOR VOLATILITY MODELS WITH COVARIATES

The asymptotic distribution of the Gaussian quasi-maximum likelihood estimator (QMLE) is obtained for a wide class of asymmetric GARCH models with exogenous covariates. The true value of the parameter is not restricted to belong to the interior of the parameter space, which allows us to derive tests for the significance of the parameters. In particular, the relevance of the exogenous variables can be assessed. The results are obtained without assuming that the innovations are independent, which allows conditioning on different information sets. Monte Carlo experiments and applications to financial series illustrate the asymptotic results. In particular, an empirical study demonstrates that the realized volatility can be a helpful covariate for predicting squared returns.

Least‐squares estimation of GARCH(1,1) models with heavy‐tailed errors

GARCH (1,1) models are widely used for modelling processes with time varying volatility. These include financial time series, which can be particularly heavy tailed. In this paper, we propose a log-transform-based least squares estimator (LSE) for the GARCH (1,1) model. The asymptotic properties of the LSE are studied under very mild moment conditions for the errors. We establish the consistency, asymptotic normality at the standard convergence rate of square root-of-n for our estimator. The finite sample properties are assessed by means of an extensive simulation study. Our results show that LSE is more accurate than the quasi-maximum likelihood estimator (QMLE) for heavy tailed errors. Finally, we provide some empirical evidence on two financial time series considering daily and high frequency returns. The results of the empirical analysis suggest that in some settings, depending on the specific measure of volatility adopted, the LSE can allow for more accurate predictions of volatility than the usual Gaussian QMLE.

Measure-Transformed Quasi-Maximum Likelihood Estimation

In this paper, the Gaussian quasi-maximum likelihood estimator (GQMLE) is generalized by applying a transform to the probability distribution of the data. The proposed estimator, called measure-transformed GQMLE (MT-GQMLE), minimizes the empirical Kullback–Leibler divergence between a transformed probability distribution of the data and a hypothesized Gaussian probability measure. By judicious choice of the transform we show that, unlike the GQMLE, the proposed estimator can gain sensitivity to higher order statistical moments and resilience to outliers leading to significant mitigation of the model mismatch effect on the estimates. Under some mild regularity conditions, we show that the MT-GQMLE is consistent, asymptotically normal and unbiased. Furthermore, we derive a necessary and sufficient condition for asymptotic efficiency. A data driven procedure for optimal selection of the measure transformation parameters is developed that minimizes the trace of an empirical estimate of the asymptotic mean-squared-error matrix. The MT-GQMLE is applied to linear regression and source localization and numerical comparisons illustrate its robustness and resilience to outliers.

Asymptotic behavior of the Laplacian quasi-maximum likelihood estimator of affine causal processes

We prove the consistency and asymptotic normality of the Laplacian Quasi-Maximum Likelihood Estimator (QMLE) for a general class of causal time series including ARMA, AR($\infty$), GARCH, ARCH($\infty$), ARMA-GARCH, APARCH, ARMA-APARCH,..., processes. We notably exhibit the advantages (moment order and robustness) of this estimator compared to the classical Gaussian QMLE. Numerical simulations confirms the accuracy of this estimator.

On Buffered Double Autoregressive Time Series Models

A buffered double autoregressive (BDAR) time series model is proposed in this paper to depict the buffering phenomenon of conditional mean and conditional variance in time series. To build this model, a novel flexible regime switch mechanism is introduced to modify the classical threshold AR model by capturing the stickiness of signal. Besides, considering the inadequacy of traditional models under the lack of information, a signal retrospection is run in this model to provide a more accurate judgement. Moreover, formal proofs suggest strict stationarity and geometric ergodicity of BDAR model under several sufficient conditions. A Gaussian quasi-maximum likelihood estimation (QMLE) is employed to compute the estimators in this model. The strict proof reveals the asymptotic normality of the estimated coefficients of double AR models. More importantly, it has been demonstrated that the estimated threshold of the BDAR model weakly converges to a functional of a two-sided compound Poisson process. Furthermore, a model selection criteria and asymptotic property have been established. Simulation studies are constructed to evaluate the finite sample performance of QMLE and model selection criteria. Finally, an empirical analysis of Hang Seng Index (HSI) using BDAR model reveals the asymmetry of investors’ preference over losses and gains as well as the asymmetry of volatility structure.

조건부 Value-at-Risk와 Expected Shortfall 추정을 위한 준모수적 방법들의 비교 연구

Basel committee suggests using Value-at-Risk (VaR) and expected shortfall (ES) as a measurement for market risk. Various estimation methods of VaR and ES have been studied in the literature. This paper compares semi-parametric methods, such as conditional autoregressive value at risk (CAViaR) and conditional autoregressive expectile (CARE) methods, and a Gaussian quasi-maximum likelihood estimator (QMLE)-based method through back-testing methods. We use unconditional coverage (UC) and conditional coverage (CC) tests for VaR, and a bootstrap test for ES to check the adequacy. A real data analysis is conducted for S&P 500 index and Hyundai Motor Co. stock price index data sets.

A New Pearson-Type QMLE for Conditionally Heteroscedastic Models

This article proposes a novel Pearson-type quasi-maximum likelihood estimator (QMLE) of GARCH(p, q) models. Unlike the existing Gaussian QMLE, Laplacian QMLE, generalized non-Gaussian QMLE, or LAD estimator, our Pearsonian QMLE (PQMLE) captures not just the heavy-tailed but also the skewed innovations. Under strict stationarity and some weak moment conditions, the strong consistency and asymptotic normality of the PQMLE are obtained. With no further efforts, the PQMLE can be applied to other conditionally heteroscedastic models. A simulation study is carried out to assess the performance of the PQMLE. Two applications to four major stock indexes and two exchange rates further highlight the importance of our new method. Heavy-tailed and skewed innovations are often observed together in practice, and the PQMLE now gives us a systematic way to capture these two coexisting features.

Residual-based rank specification tests for AR–GARCH type models

This paper derives the asymptotic distribution for a number of rank-based and classical residual specification tests in AR–GARCH type models. We consider tests for the null hypotheses of no linear and quadratic serial residual autocorrelation, residual symmetry, and no structural breaks. We also apply our method to backtesting Value-at-Risk. For these tests we show that, generally, no size correction is needed in the asymptotic test distribution when applied to AR–GARCH residuals obtained through Gaussian quasi maximum likelihood estimation. To be precise, we give exact expressions for the limiting null distribution of the test statistics applied to (standardized) residuals, and find that standard critical values often, though not always, lead to conservative tests. For this result, we give simple necessary and sufficient conditions. Simulations show that our asymptotic approximations work well for a large number of AR–GARCH models and parameter values. We also show that the rank-based tests often, though not always, have superior power properties over the classical tests, even if they are conservative. An empirical application illustrates the relevance of these tests to the AR–GARCH models for weekly stock market return indices of some major and emerging countries.

Location Multiplicative Error Model(1,1): Asymptotic Properties of a Modified QMLE

This paper extends the Multiplicative Error Model (MEM) by adding the location parameter. The minimum of a sample is proved to be a consistent estimator for this parameter, and used to truncate the data set. If the truncated data set contains none or a trivial proportion of zeroes, the autoregressive coefficients in this model are estimated by a Gaussian Quasi Maximum Likelihood Estimator (QMLE). Consistency and asymptotic normality of this estimator based on the truncated process are demonstrated under weak assumptions about random errors. If a large proportion of zeroes exist in the truncated data set, we adopt a Zero-Augmented distribution for the random errors. Such distribution consists of a probability mass assigned at zero and a continuous density function at nonzero values. We also propose a different QMLE without specifying the true density function, to estimate the probability mass and autoregressive coefficients. Similar asymptotic properties for this modified QMLE are established under weak assumptions. We present simulation studies and empirical analysis on IBM High Frequency trading data, to illustrate the asymptotic results and model improvement for both cases.

Quasi-maximum likelihood estimation for multiple volatility shifts

Abstract We propose the Gaussian quasi-maximum likelihood estimator (QMLE) to detect and locate multiple volatility shifts. Our Gaussian QMLE is shown to be consistent under suitable conditions and the rate of convergence is provided. It is also shown that the binary segmentation procedure provides a consistent estimation for the number of volatility shifts.