We describe and examine a test for a general class of shape constraints, such as signs of derivatives, U-shape, quasi-convexity, log-convexity, among others, in a nonparametric framework using partial sums empirical processes. We show that, after a suitable transformation, its asymptotic distribution is a functional of a Brownian motion index by the c.d.f. of the regressor. As a result, the test is distribution-free and critical values are readily available. However, due to the possible poor approximation of the asymptotic critical values to the finite sample ones, we also describe a valid bootstrap algorithm.

We derive a risk lower bound in estimating the threshold parameter without knowing whether the threshold regression model is continuous or not. The bound goes to zero as the sample size $ n $ grows only at the cube root rate. Motivated by this finding, we develop a continuity test for the threshold regression model and a bootstrap to compute its \textit{p}-values. The validity of the bootstrap is established, and its finite sample property is explored through Monte Carlo simulations.

We describe a (nonparametric) prediction algorithm for spatial data, based on a canonical factorization of the spectral density function. We provide theoretical results showing that the predictor has desirable asymptotic properties. Finite sample performance is assessed in a Monte Carlo study that also compares our algorithm to a rival nonparametric method based on the infinite AR representation of the dynamics of the data. Finally, we apply our methodology to predict house prices in Los Angeles.

The aim of the paper is to describe a bootstrap, contrary to the sieve boot- strap, valid under either long memory (LM) or short memory (SM) depen- dence. One of the reasons of the failure of the sieve bootstrap in our context is that under LM dependence, the sieve bootstrap may not be able to capture the true covariance structure of the original data. We also describe and ex- amine the validity of the bootstrap scheme for the least squares estimator of the parameter in a regression model and for model specification. The moti- vation for the latter example comes from the observation that the asymptotic distribution of the test is intractable.

This paper addresses inference in large panel data models in the presence of both cross-sectional and temporal dependence of unknown form. We are interested in making inferences that do not rely on the choice of any smoothing parameter as is the case with the often employed “HAC” estimator for the covariance matrix. To that end, we propose a cluster estimator for the asymptotic covariance of the estimators and valid bootstrap schemes that do not require the selection of a bandwidth or smoothing parameter and accommodate the nonparametric nature of both temporal and cross-sectional dependence. Our approach is based on the observation that the spectral representation of the fixed effect panel data model is such that the errors become approximately temporally uncorrelated. Our proposed bootstrap schemes can be viewed as wild bootstraps in the frequency domain. We present some Monte Carlo simulations to shed some light on the small sample performance of our inferential procedure.

This paper considers robust inference in threshold regression models when the practitioners do not know whether at the threshold point the true specification has a kink or a jump, nesting previous works that assume either continuity or discontinuity at the threshold. We find that the parameter values under the kink restriction are irregular points of the Hessian matrix, destroying the asymptotic normality and inducing the cube-root convergence rate for the threshold estimate. However, we are able to obtain the same asymptotic distribution as Hansen (2000) for the quasi-likelihood ratio statistic for the unknown threshold. We propose to construct confidence intervals for the threshold by bootstrap test inversion. Finite sample performances of the proposed procedures are examined through Monte Carlo simulations and an economic empirical application is given.

In empirical studies selection of the order of a model is routinely invoked. A common example is the order selection of an autoregressive model via Akaike's AIC, Schwarz's BIC or Hannan and Quinn's HIC. The criteria are based on the conditional sum of squares (CSS). However, the computation of the CSS might be difficult for some models such as Bloomfield's exponential model and/or when we allow for long memory dependence. The main aim of the article is thus to propose an alternative way to compute the criterion by using the decomposition of the variance of the innovation errors in terms of its frequency components. We show its validity to obtain the correct order the model. In addition, as a by‐product, we describe a simple (two‐step) estimator of the parameters of the model.

We examine a test for weak stationarity against alternatives that covers both local-stationarity and break point models. A key feature of the test is that its asymptotic distribution is a functional of the standard Brownian bridge sheet in [0,1]2, so that it does not depend on any unknown quantity. The test has nontrivial power against local alternatives converging to the null hypothesis at a T−1/2 rate, where T is the sample size. We also examine an easy-to-implement bootstrap analogue and present the finite sample performance in a Monte Carlo experiment. Finally, we implement the methodology to assess the stability of inflation dynamics in the United States and on a set of neuroscience tremor data.

In this paper we provide a new Central Limit Theorem for estimators of the slope papers in large dynamic panel data models (where both n and T increase without bound) in the presence of, possibly, strong cross-sectional dependence. We proceed by providing two related tests for breaks/homogeneity in the time dimension. The first test is based on the CUSUM principle; the second test is based on a Hausman–Durbin–Wu approach. Some of the key features of the tests are that they have nontrivial power when the number of individuals, for which the slope parameters may differ, is a “negligible” fraction or when the break happens to be towards the end of the sample, and do not suffer from the incidental parameter problem. We provide a simple bootstrap algorithm to obtain (asymptotic) valid critical values for our statistics. An important feature of the bootstrap is that there is no need to know the underlying model of the cross-sectional dependence. A Monte-Carlo simulation analysis sheds some light on the small sample behaviour of the tests and their bootstrap analogues. We implement our test to some real economic data.

This paper is concerned with inference in regression models with either a kink or a jump at an unknown threshold, particularly when we do not know whether the kink or jump is the true specification. One of our main results shows that the statistical properties of the estimator of the threshold parameter are substantially different under the two settings, with a slower rate of convergence under the kink design, and more surprisingly slower than if the correct kink specification were employed in the estimation. We thus propose two testing procedures to distinguish between them. Next, we develop a robust inferential procedure that does not require prior knowledge on whether the regression model is kinky or jumpy. Furthermore, we propose to construct confidence intervals for the unknown threshold by the bootstrap test inversion, also known as grid bootstrap. Finite sample performances of the bootstrap tests and the grid bootstrap confidence intervals are examined and compared against tests and confidence intervals based on the asymptotic distribution through Monte Carlo simulations. Finally, we implement our procedure to an economic empirical application

The paper examines a test for smoothness/breaks in a nonparametric regression model with dependent data. The test is based on the supremum of the difference between the one-sided kernel regression estimates. When the errors of the model exhibit strong dependence, we have that the normalization constants to obtain the asymptotic Gumbel distribution are data dependent and the critical values are difficult to obtain, if possible. This motivates, together with the fact that the rate of convergence to the Gumbel distribution is only logarithmic, the use of a bootstrap analogue of the test. We describe a valid bootstrap algorithm and show its asymptotic validity. It is interesting to remark that neither subsampling nor the sieve bootstrap will lead to asymptotic valid inferences in our scenario. Finally, we indicate how to perform a test for k breaks against the alternative of \(k+k_{0}\) breaks for some \(k_{0}\).

We consider an omnibus test for the correct specification of the dynamics of a sequence $\left\{ {x\left( t \right)} \right\}_{t \in Z^d } $ in a lattice. As it happens with causal models and d = 1, its asymptotic distribution is not pivotal and depends on the estimator of the unknown parameters of the model under the null hypothesis. One first main goal of the paper is to provide a transformation to obtain an asymptotic distribution that is free of nuisance parameters. Secondly, we propose a bootstrap analog of the transformation and show its validity. Thirdly, we discuss the results when $\left\{ {x\left( t \right)} \right\}_{t \in Z^d } $ are the errors of a parametric regression model. As a by product, we also discuss the asymptotic normality of the least squares estimator of the parameters of the regression model under very mild conditions. Finally, we present a small Monte Carlo experiment to shed some light on the finite sample behavior of our test.

Nowadays it is very frequent that a practitioner faces the problem of modelling large data sets. Some relevant examples include spatio-temporal or panel data models with large N and T. In these cases deciding a particular dynamic model for each individual/population, which plays a crucial role in prediction and inferences, can be a very onerous and complex task. The aim of this paper is thus to examine a nonparametric test for the equality of the linear dynamic models as the number of individuals increases without bound. The test has two main features: (a) there is no need to choose any bandwidth parameter and (b) the asymptotic distribution of the test is a normal random variable.

This paper examines a nonparametric CUSUM-type test for common trends in large panel data sets with individual fixed effects. We consider, as in Zhang, Su, and Phillips ( 2012), a partial linear regression model with unknown functional form for the trend component, although our test does not involve local smoothings. This conveniently forgoes the need to choose a bandwidth parameter, which due to a lack of a clear and sensible information criteria is difficult for testing purposes. We are able to do so after making use that the number of individuals increases with no limit. After removing the parametric component of the model, when the errors are homoscedastic, our test statistic converges to a Gaussian process whose critical values are easily tabulated. We also examine the consequences of having heteroscedasticity as well as discussing the problem of how to compute valid critical values due to the very complicated covariance structure of the limiting process. Finally, we present a small Monte Carlo experiment to shed some light on the finite sample performance of the test.

This article develops a method for testing the goodness-of-fit of a given parametric autoregressive conditional duration model against unspecified nonparametric alternatives. The test statistics are functions of the residuals corresponding to the quasi maximum likelihood estimate of the given parametric model, and are easy to compute. The limiting distributions of the test statistics are not free from nuisance parameters. Hence, critical values cannot be tabulated for general use. A bootstrap procedure is proposed to implement the tests, and its asymptotic validity is established. The finite sample performances of the proposed tests and several other competing ones in the literature, were compared using a simulation study. The tests proposed in this article performed well consistently throughout, and they were either the best or close to the best. None of the tests performed uniformly the best. The tests are illustrated using an empirical example.

The paper examines a Lagrange Multiplier type test for the constancy of the parameter in general models with dependent data without imposing any artificial choice of the possible location of the break. In order to prove the asymptotic behaviour of the test, we extend a strong approximation result for partial sums of a sequence of random variables. We also present a Monte-Carlo experiment to examine the finite sample performance of the test and how it compares with tests which assume some knowledge of the possible location of the break.

For over 25 years, Peter M. Robinson has continued the London School of Economics and Political Science (LSE) tradition of excellence in quantitative economic research, succeeding in the Tooke Chair of Economic Science and Statistics the likes of Ysidro Edgeworth, Friedrich von Hayek, Bill Phillips, and Denis Sargan. He has contributed to the development of modern econometrics on rigorous foundations coming from mathematical statistics and probability theory. His work on time series and nonparametric and semiparametric inference is most influential in current econometric research. His courses on econometric theory, time series, and nonparametrics have been very innovative from the pedagogic point of view and have educated many generations of graduate students in a new understanding of econometrics. He has already supervised over 20 doctoral dissertations. His service to the profession is outstanding. He is currently co-editor of the Journal of Econometrics, advisory editor of Econometric Theory, and associate editor of the Annals of Statistics, the Journal of Time Series Analysis, and Statistical Inference for Stochastic Processes. Formerly, he was co-editor of Econometrica and of Econometric Theory, and associate editor of 12

This paper proposes bootstrap assisted specification tests for the autoregressive fractionally integrated moving average model based on the Bartlett T p -process with estimated parameters whose limiting distribution under the null depends on the estimated model and the estimation method employed. The computation of the asymptotic critical values is not easy if at all possible under these circumstances. To circumvent this problem Delgado, Hidalgo, and Velasco (2005, Annals of Statistics 33, 2568–2609) proposed an asymptotically pivotal transformation of the T p -process with estimated parameters. The aim of this paper is twofold. First, to examine alternative methods based on bootstrap algorithms for estimating the distribution of the test under the null, showing its validity. And second, to study the finite-sample performance of the different alternative procedures via Monte Carlo simulation.

In a multiple time series regression model the residuals are heteroskedastic and serially correlated of unknown form. GLS estimates of the regression coefficients using kernel regression and spectral methods are shown to be adaptive, in the sense of having the same asymptotic distribution, to the first order, as GLS estimates based on knowledge of the actual heteroskedasticity and serial correlation. A Monte Carlo experiment about the performance of our estimator is described.