An empirical likelihood goodness-of-fit test for time series

Summary. Standard goodness-of-fit tests for a parametric regression model against a series of nonparametric alternatives are based on residuals arising from a fitted model. When a parametric regression model is compared with a nonparametric model, goodness-of-fit testing can be naturally approached by evaluating the likelihood of the parametric model within a nonparametric framework. We employ the empirical likelihood for an α -mixing process to formulate a test statistic that measures the goodness of fit of a parametric regression model. The technique is based on a comparison with kernel smoothing estimators. The empirical likelihood formulation of the test has two attractive features. One is its automatic consideration of the variation that is associated with the nonparametric fit due to empirical likelihood's ability to Studentize internally. The other is that the asymptotic distribution of the test statistic is free of unknown parameters, avoiding plug-in estimation. We apply the test to a discretized diffusion model which has recently been considered in financial market analysis.     

Goodness-of-Fit Tests for the Skew-Normal Distribution When the Parameters Are Estimated from the Data

In this article, tests are developed which can be used to investigate the goodness-of-fit of the skew-normal distribution in the context most relevant to the data analyst, namely that in which the parameter values are unknown and are estimated from the data. We consider five test statistics chosen from the broad Cramér–von Mises and Kolmogorov–Smirnov families, based on measures of disparity between the distribution function of a fitted skew-normal population and the empirical distribution function. The sampling distributions of the proposed test statistics are approximated using Monte Carlo techniques and summarized in easy to use tabular form. We also present results obtained from simulation studies designed to explore the true size of the tests and their power against various asymmetric alternative distributions.     

A note on diagnostic checking of the double autoregressive model

The double autoregressive model finds its use in the modelling of conditional heteroscedasticity of time series data. In view of its growing popularity, the goodness-of-fit of the model is examined. The asymptotic distributions of the residual and squared residual autocorrelations are derived. Two test statistics are then constructed which can be used to measure the adequacy of the conditional mean and conditional variance components of a fitted model. Our goodness-of-fit tests out-perform other benchmark tests such as the Ljung–Box test in simulation studies. To illustrate the testing procedure, the model is fitted to the weekly log-return series of the Hang Seng Index.     

Testing exponentiality based on Type-I censored data

The problem of goodness-of-fit for the exponential distribution when the available data are subject to Type-I censoring is discussed here. A test procedure is proposed in this case that exhibits more power as compared to existing methods. The power of the proposed test is assessed for several alternative distributions by means of Monte Carlo simulations. Finally, the proposed test is illustrated with a real data set.     

An R package for testing goodness of fit: goft

This R package implements three types of goodness-of-fit tests for some widely used probability distributions where there are unknown parameters, namely tests based on data transformations, on the ratio of two estimators of a dispersion parameter, and correlation tests. Most of the considered tests have been proved to be powerful against a wide range of alternatives and some new ones are proposed here. The package's functionality is illustrated with several examples by using some data sets from the areas of environmental studies, biology and finance, among others.     

An approximate maximum likelihood procedure for parameter estimation in multivariate discrete data regression models

This paper considers an alternative to iterative procedures used to calculate maximum likelihood estimates of regression coefficients in a general class of discrete data regression models. These models can include both marginal and conditional models and also local regression models. The classical estimation procedure is generally via a Fisher-scoring algorithm and can be computationally intensive for high-dimensional problems. The alternative method proposed here is non-iterative and is likely to be more efficient in high-dimensional problems. The method is demonstrated on two different classes of regression models.     

A goodness-of-fit test with nuisance parameters: numerical performance

Jurečková and Sen (J. Statist. Plann. Inference 91 (2000) 377–397) proposed goodness-of-fit tests for models admitting nuisance location or nuisance location and scale parameters, based on the difference of two estimators of the location parameter, that are asymptotically first-order equivalent iff the null hypothesis is true. We illustrate here the numerical performance of these tests on simulated data, demonstrating their applicability to practical problems. Comparisons are also made with the well-known Shapiro–Wilk goodness-of-fit test.     

Goodness-of-fit tests via ϕ-measures of divergence for censored data

Measures of divergence or discrepancy are used extensively in statistics in various fields. In this article, we are focusing on divergence measures that are based on a class of measures known as Csiszar's divergence measures. In particular, we propose a class of goodness-of-fit tests based on Csiszar's class of measures designed for censored survival or reliability data. Further, we derive the asymptotic distribution of the test statistic under simple and composite null hypotheses as well as under contiguous alternative hypotheses. Simulations are furnished and real data are analysed to show the performance of the proposed tests for different ?-divergence measures.     

Ordinal ridge regression with categorical predictors

In multi-category response models, categories are often ordered. In the case of ordinal response models, the usual likelihood approach becomes unstable with ill-conditioned predictor space or when the number of parameters to be estimated is large relative to the sample size. The likelihood estimates do not exist when the number of observations is less than the number of parameters. The same problem arises if constraint on the order of intercept values is not met during the iterative procedure. Proportional odds models (POMs) are most commonly used for ordinal responses. In this paper, penalized likelihood with quadratic penalty is used to address these issues with a special focus on POMs. To avoid large differences between two parameter values corresponding to the consecutive categories of an ordinal predictor, the differences between the parameters of two adjacent categories should be penalized. The considered penalized-likelihood function penalizes the parameter estimates or differences between the parameter estimates according to the type of predictors. Mean-squared error for parameter estimates, deviance of fitted probabilities and prediction error for ridge regression are compared with usual likelihood estimates in a simulation study and an application.     

The Lorenz Curve for Model Assessment in Exponential Order Statistic Models

A goodness-of-fit technique for random samples from the exponential distribution based on the sample Lorenz curve is adapted for use in the exponential order statistic (EOS) model. In the EOS model, only those observations in a random sample from the exponential distribution of unknown size N that are less than some known stopping time T are observable. The model is known as the Jelinski-Moranda model in software reliability, where it is used to estimate the number of bugs in software during development. Distributional results are derived for the distance between the sample Lorenz curve and the population Lorenz curve so that it can be used as a goodness-of-fit test statistic. Simulations show that the test has good power against several alternative distributions. Simulations also indicate that in some cases, model misspecification leads to poor parameter estimation. A plotting procedure provides a means of graphical assessment of fit.     

A review of model selection procedures relevant to the weibull distribution

A number of goodness-of-fit and model selection procedures related to the Weibull distribution are reviewed. These procedures include probability plotting, correlation type goodness-of-fit tests, and chi-square goodness-of-fit tests. Also the Kolmogorow-Smirniv, Kuiper, and Cramer-Von Mises test statistics for completely specified hypothesis based on censored data are reviewed, and these test statistics based on complete samples for the unspecified parameters case are considered. Goodness-of-fit tests based on sample spacings, and a goodness-of-fit test for the Weibull process, is also discussed.

Model selection procedures for selecting between a Weibull and gamma model, a Weibull and lognormal model, and for selecting from among all three models are considered. Also tests of exponential versus Weibull and Weibull versus generalized gamma are mentioned.     

GIL-PELAEZ-ROSÉN TRANSFORMATION OF DATA

Several statistics based on the empirical characteristic function have been proposed for testing the simple goodness-of-fit hypothesis that the data come from a population with a completely specified characteristic function which cannot be inverted in a closed form, the typical example being the class of stable characteristic functions. As an alternative approach, it is pointed out here that the inversion formula of Gil-Pelaez and Rosén, as applied to the data and the hypothetical characteristic function via numerical integration, is the natural replacement of the probability integral transformation in the given situation. The transformed sample is from the uniform (0, l) distribution if and only if the null hypothesis is true, and for testing uniformity on (0,1) the whole arsenal of methods statistics so far produced can be used.     

A model-averaging approach for smoothing spline regression

ABSTRACT

This article considers nonparametric regression problems and develops a model-averaging procedure for smoothing spline regression problems. Unlike most smoothing parameter selection studies determining an optimum smoothing parameter, our focus here is on the prediction accuracy for the true conditional mean of Y given a predictor X. Our method consists of two steps. The first step is to construct a class of smoothing spline regression models based on nonparametric bootstrap samples, each with an appropriate smoothing parameter. The second step is to average bootstrap smoothing spline estimates of different smoothness to form a final improved estimate. To minimize the prediction error, we estimate the model weights using a delete-one-out cross-validation procedure. A simulation study has been performed by using a program written in R. The simulation study provides a comparison of the most well known cross-validation (CV), generalized cross-validation (GCV), and the proposed method. This new method is straightforward to implement, and gives reliable performances in simulations.     

Nonlinear GCV and quasi-GCV for shrinkage models

The generalized cross-validation (GCV) method has been a popular technique for the selection of tuning parameters for smoothing and penalty, and has been a standard tool to select tuning parameters for shrinkage models in recent works. Its computational ease and robustness compared to the cross-validation method makes it competitive for model selection as well. It is well known that the GCV method performs well for linear estimators, which are linear functions of the response variable, such as ridge estimator. However, it may not perform well for nonlinear estimators since the GCV emphasizes linear characteristics by taking the trace of the projection matrix. This paper aims to explore the GCV for nonlinear estimators and to further extend the results to correlated data in longitudinal studies. We expect that the nonlinear GCV and quasi-GCV developed in this paper will provide similar tools for the selection of tuning parameters in linear penalty models and penalized GEE models.     

A goodness-of-fit test for multivariate multiparameter copulas based on multiplier central limit theorems

Recent large scale simulations indicate that a powerful goodness-of-fit test for copulas can be obtained from the process comparing the empirical copula with a parametric estimate of the copula derived under the null hypothesis. A first way to compute approximate p-values for statistics derived from this process consists of using the parametric bootstrap procedure recently thoroughly revisited by Genest and Rémillard. Because it heavily relies on random number generation and estimation, the resulting goodness-of-fit test has a very high computational cost that can be regarded as an obstacle to its application as the sample size increases. An alternative approach proposed by the authors consists of using a multiplier procedure. The study of the finite-sample performance of the multiplier version of the goodness-of-fit test for bivariate one-parameter copulas showed that it provides a valid alternative to the parametric bootstrap-based test while being orders of magnitude faster. The aim of this work is to extend the multiplier approach to multivariate multiparameter copulas and study the finite-sample performance of the resulting test. Particular emphasis is put on elliptical copulas such as the normal and the t as these are flexible models in a multivariate setting. The implementation of the procedure for the latter copulas proves challenging and requires the extension of the Plackett formula for the t distribution to arbitrary dimension. Extensive Monte Carlo experiments, which could be carried out only because of the good computational properties of the multiplier approach, confirm in the multivariate multiparameter context the satisfactory behavior of the goodness-of-fit test.     

Homogeneity testing in a Weibull mixture model

The mixed Weibull distribution provides a flexible model to analyze random durations in a possibly heterogeneous population. To test for homogeneity against unobserved heterogeneity in a Weibull mixture model, a dispersion score test and a goodness-of-fit test are investigated. The empirical power of these tests is assessed and compared on a broad range of alternatives. It comes out that the dispersion score test, as it is based on a Weibull-to-exponential transformation, often breaks down. A simple new procedure is introduced for Weibull mixtures in scale, which combines the dispersion score test and the goodness-of-fit test. The new test is compared with several known procedures and shown to have a good overall power. To detect mixtures in shape and scale, a goodness-of-fit test is recommended. This research has been partially sponsored by a grant of the Deutsche Forschungsgemeinschaft. We thank Lars Haferkamp for computational assistance and Wilfried Seidel and a referee for their remarks on alternative test procedures.     

Random number generators for the generalized Birnbaum–Saunders distribution

The generalized Birnbaum–Saunders distribution pertains to a class of lifetime models including both lighter and heavier tailed distributions. This model adapts well to lifetime data, even when outliers exist, and has other good theoretical properties and application perspectives. However, statistical inference tools may not exist in closed form for this model. Hence, simulation and numerical studies are needed, which require a random number generator. Three different ways to generate observations from this model are considered here. These generators are compared by utilizing a goodness-of-fit procedure as well as their effectiveness in predicting the true parameter values by using Monte Carlo simulations. This goodness-of-fit procedure may also be used as an estimation method. The quality of this estimation method is studied here. Finally, through a real data set, the generalized and classical Birnbaum–Saunders models are compared by using this estimation method.     

CLONING DATA: GENERATING DATASETS WITH EXACTLY THE SAME MULTIPLE LINEAR REGRESSION FIT

This paper presents a simple computational procedure for generating ‘matching’ or ‘cloning’ datasets so that they have exactly the same fitted multiple linear regression equation. The method is simple to implement and provides an alternative to generating datasets under an assumed model. The advantage is that, unlike the case for the straight model‐based alternative, parameter estimates from the original data and the generated data do not include any model error. This distinction suggests that ‘same fit’ procedures may provide a general and useful alternative to model‐based procedures, and have a wide range of applications. For example, as well as being useful for teaching, cloned datasets can provide a model‐free way of confidentializing data.     

Default Bayesian goodness-of-fit tests for the skew-normal model

In this paper we propose a series of goodness-of-fit tests for the family of skew-normal models when all parameters are unknown. As the null distributions of the considered test statistics depend only on asymmetry parameter, we used a default and proper prior on skewness parameter leading to the prior predictive p-value advocated by G. Box. Goodness-of-fit tests, here proposed, depend only on sample size and exhibit full agreement between nominal and actual size. They also have good power against local alternative models which also account for asymmetry in the data.     

Strategies for inference robustness in focused modelling

Advances in computation mean that it is now possible to fit a wide range of complex models to data, but there remains the problem of selecting a model on which to base reported inferences. Following an early suggestion of Box & Tiao, it seems reasonable to seek 'inference robustness' in reported models, so that alternative assumptions that are reasonably well supported would not lead to substantially different conclusions. We propose a four-stage modelling strategy in which we iteratively assess and elaborate an initial model, measure the support for each of the resulting family of models, assess the influence of adopting alternative models on the conclusions of primary interest, and identify whether an approximate model can be reported. The influence-support plot is then introduced as a tool to aid model comparison. The strategy is semi-formal, in that it could be embedded in a decision-theoretic framework but requires substantive input for any specific application. The one restriction of the strategy is that the quantity of interest, or 'focus', must retain its interpretation across all candidate models. It is, therefore, applicable to analyses whose goal is prediction, or where a set of common model parameters are of interest and candidate models make alternative distributional assumptions. The ideas are illustrated by two examples. Technical issues include the calibration of the Kullback-Leibler divergence between marginal distributions, and the use of alternative measures of support for the range of models fitted.