Quadratic inference functions for varying-coefficient models with longitudinal data.

Motivated by recent data analyses in biomedical imaging studies, we consider a class of image-on-scalar regression models for imaging responses and scalar predictors. We propose using flexible multivariate splines over triangulations to handle the irregular domain of the objects of interest on the images, as well as other characteristics of images. The proposed estimators of the coefficient functions are proved to be root-n consistent and asymptotically normal under some regularity conditions. We also provide a consistent and computationally efficient estimator of the covariance function. Asymptotic pointwise confidence intervals and data-driven simultaneous confidence corridors for the coefficient functions are constructed. Our method can simultaneously estimate and make inferences on the coefficient functions while incorporating spatial heterogeneity and spatial correlation. A highly efficient and scalable estimation algorithm is developed. Monte Carlo simulation studies are conducted to examine the finite-sample performance of the proposed method, which is then applied to the spatially normalized positron emission tomography data of the Alzheimer's Disease Neuroimaging Initiative.

Semiparametric models are often considered for analyzing longitudinal data for a good balance between flexibility and parsimony. In this paper, we study a class of marginal partially linear quantile models with possibly varying coefficients. The functional coefficients are estimated by basis function approximations. The estimation procedure is easy to implement, and it requires no specification of the error distributions. The asymptotic properties of the proposed estimators are established for the varying coefficients as well as for the constant coefficients. We develop rank score tests for hypotheses on the coefficients, including the hypotheses on the constancy of a subset of the varying coefficients. Hypothesis testing of this type is theoretically challenging, as the dimensions of the parameter spaces under both the null and the alternative hypotheses are growing with the sample size. We assess the finite sample performance of the proposed method by Monte Carlo simulation studies, and demonstrate its value by the analysis of an AIDS data set, where the modeling of quantiles provides more comprehensive information than the usual least squares approach.

The generalized estimating equations (GEE) approach has attracted considerable interest for the analysis of correlated response data. This paper considers the model selection criterion based on the multivariate quasi‐likelihood (MQL) in the GEE framework. The GEE approach is closely related to the MQL. We derive a necessary and sufficient condition for the uniqueness of the risk function based on the MQL by using properties of differential geometry. Furthermore, we establish a formal derivation of model selection criterion as an asymptotically unbiased estimator of the prediction risk under this condition, and we explicitly take into account the effect of estimating the correlation matrix used in the GEE procedure.

We provide sufficient conditions for estimating from longitudinal data the causal effect of a time-dependent exposure or treatment on the marginal probability of response for a dichotomous outcome. We then show how one can estimate this effect under these conditions using the g-computation algorithm of Robins. We also derive the conditions under which some current approaches to the analysis of longitudinal data, such as the generalized estimating equations (GEE) approach of Zeger and Liang, the feedback model techniques of Liang and Zeger, and within-subject conditional methods, can provide valid tests and estimates of causal effects. We use our methods to estimate the causal effect of maternal stress on the marginal probability of a child's illness from the Mothers' Stress and Children's Morbidity data and compare our results with those previously obtained by Zeger and Liang using a GEE approach.

The present paper deals with the comparison of the performance of different estimation methods for regression models with correlated binary responses. Throughout, we consider probit models where an underlying latent continous random variable crosses a threshold. The error variables in the unobservable latent model are assumed to be normally distributed. The estimation procedures considered are (1) marginal maximum likelihood estimation using Gauss-Hermite quadrature, (2) generalized estimation equations (GEE) techniques with an extension to estimate tetrachoric correlations in a second step, and, (3) the MECOSA approach proposed by Schepers, Arminger and Kusters (1991) using hierarchical mean and covariance structure models. We present the results of a simulation study designed to evaluate the small sample properties of the different estimators and to make some comparisons with respect to technical aspects of the estimation procedures and to bias and mean squared error of the estimators. The results show that the calculation of the ML estimator requires the most computing time, followed by the MECOSA estimator. For small and moderate sample sizes the calculation of the MECOSA estimator is problematic because of problems of convergence as well as a tendency of underestimating the variances. In large samples with moderate or high correlations of the errors in the latent model, the MECOSA estimators are not as efficient as ML or GEE estimators. The higher the `true' value of an equicorrelation structure in the latent model and the larger the sample sizes are, the more is the efficiency gain of the ML estimator compared to the GEE and MECOSA estimators. Using the GEE approach, the ML estimates of tetrachoric correlations calculated in a second step are biased to a smaller extent than using the MECOSA approach.

In this paper we apply model selection criteria in time series and regression analysis to the estimation of the number of signals in the MUSIC (multiple signal classification) method. We compare the following model selection (information) criteria: AIC, HQ, BIC, AICC, and the recently introduced WIC as the weighted average of AICC and BIC. The general form of the above information criteria consists of a log likelihood function expressed in terms of the eigenvalues of the covariance matrix and a unique penalty term. In our estimation procedure, the number of signals is obtained by minimizing each of the above criteria. A linear antenna array example is presented to compare the performance of the above model selection criteria in signal processing problem.

In linear mixed model selection under ridge regression, we propose the model selection criteria based on conceptual predictive () statistic.The first proposed criterion is marginal ridge Cp () statistic based on the expected marginal Gauss discrepancy. An improvement of MRCp (IMRCp) statistic is then suggested and demonstrated, which is also an asymptotically unbiased estimator of the expected marginal Gauss discrepancy. Finally, a real data analysis and a Monte Carlo simulation study are given to examine the performance of the proposed criteria.

SummaryThis paper provides consistent information criteria for the selection of forecasting models that use a subset of both the idiosyncratic and common factor components of a big dataset. This hybrid model approach has been explored by recent empirical studies to relax the strictness of pure factor‐augmented model approximations, but no formal model selection procedures have been developed. The main difference to previous factor‐augmented model selection procedures is that we must account for estimation error in the idiosyncratic component as well as the factors. Our main contribution is to show the conditions required for selection consistency of a class of information criteria that reflect this additional source of estimation error. We show that existing factor‐augmented model selection criteria are inconsistent in circumstances where N is of larger order than , where N and T are the cross‐section and time series dimensions of the dataset respectively, and that the standard Bayesian information criterion is inconsistent regardless of the relationship between N and T. We therefore propose a new set of information criteria that guarantee selection consistency in the presence of estimated idiosyncratic components. The properties of these new criteria are explored through a Monte Carlo simulation study. The paper concludes with an empirical application to long‐horizon exchange rate forecasting using a recently proposed model with country‐specific idiosyncratic components from a panel of global exchange rates.

In this chapter we consider dependent data but move from the linear models of Chap.8 to general regression models. As in Chap.6, we consider generalized linear models (GLMs) and, more briefly, nonlinear models. We first give an outline of this chapter. In Sect.9.2 we describe three motivating datasets to which we return throughout the chapter. The GLMs discussed in Sect.6.3 can be extended to incorporate dependences in observations on the same unit; as with the linear model, an obvious way to carry out modeling in this case is to introduce unit-specific random effects. Within a GLM a natural approach is for these random effects to be included on the linear predictor scale. The resultant conditional models are known as generalized linear mixed models (GLMMs), and these are introduced in Sect.9.3. In Sects.9.4 and9.5 we describe likelihood and conditional likelihood methods of estimation, with Sect.9.6 devoted to a Bayesian treatment. Section9.7 illustrates some of the flexibility of GLMMs by describing and applying a particular model for spatial dependence. An alternative random effects specification, based on conjugacy, is described in Sect.9.8. An important approach to the modeling and analysis of dependent data that is philosophically different from the random effects formulation is via marginal models and generalized estimating equations (GEE), and these are the subject of Sect.9.9. In Sect.9.10, a second GEE approach is described in which the estimating equations for the mean are supplemented with a second set for the variances/covariances. For GLMMs, extra care must be taken with parameter interpretation, and Sect.9.11 discusses this issue, emphasizing how interpretation differs between conditional and marginal models. In PartII of the book, which focused on independent data, Chap.7 was devoted to models for binary data. For dependent data, models binary data are less well developed, and so we do not devote a complete chapter to their description. However, Sect.9.12 introduces the modeling of dependent binary data, and, subsequently, Sects.9.13 and 9.14 describe conditional (mixed) and marginal models for binary data. Section 9.15 considers how nonlinear models, as defined in Sect.6.10, can be extended to the dependent data case. For such models, many applications concentrate on inference for units, and so the introduction of random effects is again suggested. We refer to the resultant class of models as nonlinear mixed models (NLMMs). Section9.16 considers issues related to the parameterization of the nonlinear model. Inference for nonlinear mixed models via likelihood and Bayes approaches is covered in Sects.9.17 and9.18, while GEE is briefly considered in Sect.9.19. The assessment of assumptions for general regression models is described in Sect.9.20, with concluding comments contained in Sect.9.21. Additional references appear in Sect.9.22.

In causal randomized experiments or psychological trials, the two-stage least squares (2SLS) model with instrument variables (IVs) is a widely used approach to address the issue of treatment endogeneity. The IVs are used to estimate a part of the causal effect whose estimation is not affected by the violation of the linearity assumption in the causal model, and the causal effect of interest in the 2SLS model becomes the local average treatment effect (LATE). Because practical data usually violate the normality assumption, the LATE estimate from the traditional normal-distribution-based method may be inefficient or even biased. This study proposes a robust Bayesian estimation method using Student’s t distributions to model data with heavy tails or containing outliers and compares the performance of the proposed robust method to that of the traditional normal-distribution-based method. A Monte Carlo simulation study is conducted and shows that the proposed robust method outperforms the traditional method when data are contaminated. The robust method provides more accurate and efficient LATE estimates and better model fits and thus is recommended to be used in general in the 2SLS modeling with IVs.

In this article, we consider the varying-coefficient quantile regression model with a power transformation on the dependent variable. The functional coefficients are estimated by the use of B-spline and the number of knots is chosen according to Schwarz-type Information Criterion. The transformation parameter is estimated by minimizing the cusum residual square sum. We show that the estimates of transformation parameter and the functional coefficients are consistent, and also obtain the rates of convergence of the estimation of functional coefficients. The proposed methods are illustrated by some simulated studies and a real data example.

Longitudinal data often encounter missingness with monotone and/or intermittent missing patterns. Multiple imputation (MI) has been popularly employed for analysis of missing longitudinal data. In particular, the MI-GEE method has been proposed for inference of generalized estimating equations (GEE) when missing data are imputed via MI. However, little is known about how to perform model selection with multiply imputed longitudinal data. In this work, we extend the existing GEE model selection criteria, including the "quasi-likelihood under the independence model criterion" (QIC) and the "missing longitudinal information criterion" (MLIC), to accommodate multiple imputed datasets for selection of the MI-GEE mean model. According to real data analyses from a schizophrenia study and an AIDS study, as well as simulations under nonmonotone missingness with moderate proportion of missing observations, we conclude that: (i) more than a few imputed datasets are required for stable and reliable model selection in MI-GEE analysis; (ii) the MI-based GEE model selection methods with a suitable number of imputations generally perform well, while the naive application of existing model selection methods by simply ignoring missing observations may lead to very poor performance; (iii) the model selection criteria based on improper (frequentist) multiple imputation generally performs better than their analogies based on proper (Bayesian) multiple imputation.

Ocean tomography [W. Munk and C. Wunsch, Deep Sea Res. 26, 123–61 (1979)] introduces several complications beyond those of conventional inverse theory. The ocean environment represents a significant challenge to the problems of time keeping and data handling. Further, the ocean is a randomly fluctuating medium that changes rapidly in time. These random effects must be either utilized or filtered out by estimation procedures before inverse problems in underwater acoustics can be solved. The random effects are most significant when amplitude ocean acoustic tomography is attempted because micromultipath interference can cause large amplitude discrepancies. A previous attempt to invert for sound-speed structure in a randomly fluctuating ocean failed [M. Brown, U. Calif. San Diego, Ph.D. thesis (1992)]. This paper outlines a successful method for inversion in a randomly fluctuating medium. Simple random inverse problems, such as two-dimensional travel time and one-dimensional waves, are studied. Criteria for stability, uniqueness and model resolution are established. The size of the fluctuations and the extent of the randomness are varied, and an iterative scheme for higher order terms is discussed. The paper provides an analysis of the stochastic forward or direct problem. Parametric and nonparametric estimation procedures are used to solve the inverse problem, and estimator and filter performance are analyzed. Computer solutions to simulated random inverse problems are given. This work is ongoing and will culminate in a successful solution to the random ocean inverse problem.

Longitudinal categorical data are often collected using an experimental design where the interest is in the differential development of the treatment group compared to the control group. Such differential development is often assessed based on average growth curves but can also be based on transitions. For longitudinal multinomial data we describe a transitional methodology for the statistical analysis based on a distance model. Such a distance approach has two advantages compared to a multinomial regression model: (1) sparse data can be handled more efficiently; (2) a graphical representation of the model can be made to enhance interpretation. Within this approach it is possible to jointly model the observations and missing values by adding a new category to the response variable representing the missingness condition. This approach is investigated in a Monte Carlo simulation study. The results show this is a promising way to deal with missing data, although the mechanism is not yet completely understood in all cases. Finally, an empirical example is presented where the advantages of the modeling procedure are highlighted.

Finding a new drug which is both safe and efficient is an expensive and time-consuming endeavour. In particular, establishing the ‘dose-effect relationship’ – how beneficial a drug is at different dosages – can be challenging. Predicting this curve requires gathering experimental data by exposing and recording how cells respond to various levels of the drug. However, extreme values are often observed at low and high dosages, potentially introducing errors that are hard to correct in the prediction process. Yet, these extreme observations are sometimes genuine so researchers cannot just ignore them. To improve dose-effect estimation, Zhou, Liu, Fang et al. developed a new general-purpose approach. It uses advanced statistical modelling to account for extremes in lab data. This strategy outperformed other methods when dealing with these observations while also providing higher efficiency in data analysis with more uniform data in experiments. To facilitate implementation, Zhou, Liu, Fang et al. set up a user-friendly tool baptized ‘REAP’; this free online resource allows scientists without advanced statistical experience to harness the new approach and to perform dose-effect analysis more easily and accurately. This could boost research across many different disciplines that examine the effects of chemicals on cells.