A nonparametric procedure for the two-factor mixed model with missing data

We develop a nonparametric imputation technique to test for the treatment effects in a nonparametric two-factor mixed model with incomplete data. Within each block, an arbitrary covariance structure of the repeated measurements is assumed without the explicit parametrization of the joint multivariate distribution. The number of repeated measurements is uniformly bounded whereas the number of blocks tends to infinity. The essential idea of the nonparametric imputation is to replace the unknown indicator functions of pairwise comparisons by the corresponding empirical distribution functions. The proposed nonparametric imputation method holds valid under the missing completely at random (MCAR) mechanism. We apply the nonparametric imputation on Brunner and Dette's method for the nonparametric two-factor mixed model and this extension results in a weighted partial rank transform statistic. Asymptotic relative efficiency of the nonparametric imputation method with the complete data versus the incomplete data is derived to quantify the efficiency loss due to the missing data. Monte Carlo simulation studies are conducted to demonstrate the validity and power of the proposed method in comparison with other existing methods. A migraine severity score data set is analyzed to demonstrate the application of the proposed method in the analysis of missing data.     

Fitting time-dependent multicompartment models: a case study

A multicompartment model with time-dependent transfer rates is fitted to data on ovarian follicle dynamics in mice. The fitted model arises from an interplay between parametric and nonparametric approaches to fitting curves to these data. Nonparametric regression estimates, in the form of spline smoothers, are used in conjunction with the biologically meaningful general class of multicompartment models to suggest refinements to the parametric model. One result of this interplay is the suggestion of using three-stage step functions for the compartmental transition rates; the resulting curves mimic closely the nonparametric regression estimates.     

Bayesian nonparametric regression analysis of data with random effects covariates from longitudinal measurements

We consider nonparametric regression analysis in a generalized linear model (GLM) framework for data with covariates that are the subject-specific random effects of longitudinal measurements. The usual assumption that the effects of the longitudinal covariate processes are linear in the GLM may be unrealistic and if this happens it can cast doubt on the inference of observed covariate effects. Allowing the regression functions to be unknown, we propose to apply Bayesian nonparametric methods including cubic smoothing splines or P-splines for the possible nonlinearity and use an additive model in this complex setting. To improve computational efficiency, we propose the use of data-augmentation schemes. The approach allows flexible covariance structures for the random effects and within-subject measurement errors of the longitudinal processes. The posterior model space is explored through a Markov chain Monte Carlo (MCMC) sampler. The proposed methods are illustrated and compared to other approaches, the "naive" approach and the regression calibration, via simulations and by an application that investigates the relationship between obesity in adulthood and childhood growth curves.     

Dose-response curve estimation: a semiparametric mixture approach

In the estimation of a dose-response curve, parametric models are straightforward and efficient but subject to model misspecifications; nonparametric methods are robust but less efficient. As a compromise, we propose a semiparametric approach that combines the advantages of parametric and nonparametric curve estimates. In a mixture form, our estimator takes a weighted average of the parametric and nonparametric curve estimates, in which a higher weight is assigned to the estimate with a better model fit. When the parametric model assumption holds, the semiparametric curve estimate converges to the parametric estimate and thus achieves high efficiency; when the parametric model is misspecified, the semiparametric estimate converges to the nonparametric estimate and remains consistent. We also consider an adaptive weighting scheme to allow the weight to vary according to the local fit of the models. We conduct extensive simulation studies to investigate the performance of the proposed methods and illustrate them with two real examples.     

Bioprocess iterative batch-to-batch optimization based on hybrid parametric/nonparametric models

This paper presents a novel method for iterative batch-to-batch dynamic optimization of bioprocesses. The relationship between process performance and control inputs is established by means of hybrid grey-box models combining parametric and nonparametric structures. The bioreactor dynamics are defined by material balance equations, whereas the cell population subsystem is represented by an adjustable mixture of nonparametric and parametric models. Thus optimizations are possible without detailed mechanistic knowledge concerning the biological system. A clustering technique is used to supervise the reliability of the nonparametric subsystem during the optimization. Whenever the nonparametric outputs are unreliable, the objective function is penalized. The technique was evaluated with three simulation case studies. The overall results suggest that the convergence to the optimal process performance may be achieved after a small number of batches. The model unreliability risk constraint along with sampling scheduling are crucial to minimize the experimental effort required to attain a given process performance. In general terms, it may be concluded that the proposed method broadens the application of the hybrid parametric/nonparametric modeling technique to "newer" processes with higher potential for optimization.     

Evaluating decision rules for nitrogen fertilization

It is important, both for farmer profit and for the environment, to correctly dose nitrogen fertilizer for crop growth. Fertilizer recommendations are embodied in decision rules, which give a recommended dose of nitrogen (N) as a function of information available at the time the decision is made. In this paper, we first propose a criterion for evaluating decision rules. The proposed criterion is the expectation of the objective function when the decision rule is implemented. The major problem here is the estimation of this criterion. Two estimators are considered, a model-based and a nonparametric estimator. A simulation study shows that, in essentially all cases, the nonparametric estimator is better or no worse than the model-based estimator. The bias in the nonparametric estimator is always very small.     

Modeling longitudinal data with nonparametric multiplicative random effects jointly with survival data

Summary .   In clinical studies, longitudinal biomarkers are often used to monitor disease progression and failure time. Joint modeling of longitudinal and survival data has certain advantages and has emerged as an effective way to mutually enhance information. Typically, a parametric longitudinal model is assumed to facilitate the likelihood approach. However, the choice of a proper parametric model turns out to be more elusive than models for standard longitudinal studies in which no survival endpoint occurs. In this article, we propose a nonparametric multiplicative random effects model for the longitudinal process, which has many applications and leads to a flexible yet parsimonious nonparametric random effects model. A proportional hazards model is then used to link the biomarkers and event time. We use B-splines to represent the nonparametric longitudinal process, and select the number of knots and degrees based on a version of the Akaike information criterion (AIC). Unknown model parameters are estimated through maximizing the observed joint likelihood, which is iteratively maximized by the Monte Carlo Expectation Maximization (MCEM) algorithm. Due to the simplicity of the model structure, the proposed approach has good numerical stability and compares well with the competing parametric longitudinal approaches. The new approach is illustrated with primary biliary cirrhosis (PBC) data, aiming to capture nonlinear patterns of serum bilirubin time courses and their relationship with survival time of PBC patients.     

Hypothesis testing in semiparametric additive mixed models

We consider testing whether the nonparametric function in a semiparametric additive mixed model is a simple fixed degree polynomial, for example, a simple linear function. This test provides a goodness-of-fit test for checking parametric models against nonparametric models. It is based on the mixed-model representation of the smoothing spline estimator of the nonparametric function and the variance component score test by treating the inverse of the smoothing parameter as an extra variance component. We also consider testing the equivalence of two nonparametric functions in semiparametric additive mixed models for two groups, such as treatment and placebo groups. The proposed tests are applied to data from an epidemiological study and a clinical trial and their performance is evaluated through simulations.     

Fitting mixture models to birth weight data: a case study.

Birth weights by gestational age are compared in two birth cohorts from Northern Finland, the first from 1966 and the second from 1985-1986. A curious fact in the data is that mean birth weight before the 39th week was lower in the latter series although the mean birth weight for the total series was higher. Similar findings have been reported in other series. A mixture model with the nonparametric regression function is proposed for studying the hypothesis that the difference was caused by more frequent gross errors in gestational assessment in the earlier cohort. The probability of an error in gestational assessment then greatly depends on the observed gestational age, which makes the mixture model nonstandard. Maximum likelihood solutions to the parameters in the proposed model were computed employing the general expectation-maximization (EM) algorithm. A technique for studying the effect of errors on the intrauterine weight gain curve is proposed and applied to our two birth cohorts. The risk of underestimation of gestational age seems to be larger in the previous series and the differences between the growth curves almost totally vanish when "corrected" by means of the mixture model.     

Robust estimation for ordinary differential equation models

Applied scientists often like to use ordinary differential equations (ODEs) to model complex dynamic processes that arise in biology, engineering, medicine, and many other areas. It is interesting but challenging to estimate ODE parameters from noisy data, especially when the data have some outliers. We propose a robust method to address this problem. The dynamic process is represented with a nonparametric function, which is a linear combination of basis functions. The nonparametric function is estimated by a robust penalized smoothing method. The penalty term is defined with the parametric ODE model, which controls the roughness of the nonparametric function and maintains the fidelity of the nonparametric function to the ODE model. The basis coefficients and ODE parameters are estimated in two nested levels of optimization. The coefficient estimates are treated as an implicit function of ODE parameters, which enables one to derive the analytic gradients for optimization using the implicit function theorem. Simulation studies show that the robust method gives satisfactory estimates for the ODE parameters from noisy data with outliers. The robust method is demonstrated by estimating a predator-prey ODE model from real ecological data.     

Semiparametric regression for periodic longitudinal hormone data from multiple menstrual cycles

We consider semiparametric regression for periodic longitudinal data. Parametric fixed effects are used to model the covariate effects and a periodic nonparametric smooth function is used to model the time effect. The within-subject correlation is modeled using subject-specific random effects and a random stochastic process with a periodic variance function. We use maximum penalized likelihood to estimate the regression coefficients and the periodic nonparametric time function, whose estimator is shown to be a periodic cubic smoothing spline. We use restricted maximum likelihood to simultaneously estimate the smoothing parameter and the variance components. We show that all model parameters can be easily obtained by fitting a linear mixed model. A common problem in the analysis of longitudinal data is to compare the time profiles of two groups, e.g., between treatment and placebo. We develop a scaled chi-squared test for the equality of two nonparametric time functions. The proposed model and the test are illustrated by analyzing hormone data collected during two consecutive menstrual cycles and their performance is evaluated through simulations.     

Approximate nonparametric corrected-score method for joint modeling of survival and longitudinal data measured with error

We consider the problem of jointly modeling survival time and longitudinal data subject to measurement error. The survival times are modeled through the proportional hazards model and a random effects model is assumed for the longitudinal covariate process. Under this framework, we propose an approximate nonparametric corrected-score estimator for the parameter, which describes the association between the time-to-event and the longitudinal covariate. The term nonparametric refers to the fact that assumptions regarding the distribution of the random effects and that of the measurement error are unnecessary. The finite sample size performance of the approximate nonparametric corrected-score estimator is examined through simulation studies and its asymptotic properties are also developed. Furthermore, the proposed estimator and some existing estimators are applied to real data from an AIDS clinical trial.     

Using semiparametric‐mixed model and functional linear model to detect vulnerable prenatal window to carcinogenic polycyclic aromatic hydrocarbons on fetal growth

Prenatal exposure to carcinogenic polycyclic aromatic hydrocarbons (c‐PAHs) through maternal inhalation induces higher risk for a wide range of fetotoxic effects. However, the most health‐relevant dose function from chronic gestational exposure remains unclear. Whether there is a gestational window during which the human embryo/fetus is particularly vulnerable to PAHs has not been examined thoroughly. We consider a longitudinal semiparametric‐mixed effect model to characterize the individual prenatal PAH exposure trajectory, where a nonparametric cyclic smooth function plus a linear function are used to model the time effect and random effects are used to account for the within‐subject correlation. We propose a penalized least squares approach to estimate the parametric regression coefficients and the nonparametric function of time. The smoothing parameter and variance components are selected using the generalized cross‐validation (GCV) criteria. The estimated subject‐specific trajectory of prenatal exposure is linked to the birth outcomes through a set of functional linear models, where the coefficient of log PAH exposure is a fully nonparametric function of gestational age. This allows the effect of PAH exposure on each birth outcome to vary at different gestational ages, and the window associated with significant adverse effect is identified as a vulnerable prenatal window to PAHs on fetal growth. We minimize the penalized sum of squared errors using a spline‐based expansion of the nonparametric coefficient function to draw statistical inferences, and the smoothing parameter is chosen through GCV.     

Nonparametric estimation of the effects of quantitative trait loci

Interval mapping of quantitative trait loci from breeding experiments plays an important role in understanding the mechanisms of disease, both in humans and other organisms. Standard approaches to estimation involve parametric assumptions for the component distributions and may be sensitive to model misspecification. Some nonparametric tests have been studied. However, nonparametric estimation of the phenotypic distributions has not been considered in the genetics literature, even though such methods might provide essential nonparametric summaries for comparing different loci. We develop a sufficient condition for identifiability of the phenotypic distributions. Simple nonparametric estimators for the distributions are proposed for uncensored and right censored data. They have a closed form and their small and large sample properties are readily established. Their practical utility as numerical summaries which complement nonparametric tests is demonstrated on two recent genetics examples.     

Likelihood, parsimony, and heterogeneous evolution

Evolutionary rates vary among sites and across the phylogenetic tree (heterotachy). A recent analysis suggested that parsimony can be better than standard likelihood at recovering the true tree given heterotachy. The authors recommended that results from parsimony, which they consider to be nonparametric, be reported alongside likelihood results. They also proposed a mixture model, which was inconsistent but better than either parsimony or standard likelihood under heterotachy. We show that their main conclusion is limited to a special case for the type of model they study. Their mixture model was inconsistent because it was incorrectly implemented. A useful nonparametric model should perform well over a wide range of possible evolutionary models, but parsimony does not have this property. Likelihood-based methods are therefore the best way to deal with heterotachy.     

Nonparametric Analysis of Ordered Categorical Data in Designs with Longitudinal Observations and Small Sample Sizes

For designs with longitudinal observations of ordered categorical data, a nonparametric model is considered where treatment effects and interactions are defined by means of the marginal distributions. These treatment effects are estimated consistently by ranking methods. The hypotheses in this nonparametric setup are formulated by means of the distribution functions. The asymptotic distribution of the estimators for the nonparametric effects are given under the hypotheses. For small samples, a rather accurate approximation is suggested. A clinical trial with ordered categorical data is used to motivate the ideas and to explain the procedures which are extensions of the Wilcoxon‐Mann‐Whitney test to factorial designs with longitudinal observations. The application of the procedures requires only some trivial regularity assumptions.     

Modeling a Poisson forest in variable elevations: a nonparametric Bayesian approach

A nonparametric Bayesian formulation is given to the problem of modeling nonhomogeneous spatial point patterns influenced by concomitant variables. Only incomplete information on the concomitant variables is assumed, consisting of a relatively small number of point measurements. Residual variation, caused by other unmeasured influential factors, is modeled in terms of a spatially varying baseline intensity function. A Markov chain Monte Carlo scheme is proposed for the simultaneous nonparametric estimation of each unknown function in the model. The suggested method is illustrated by reanalysing a data set in Rathbun (1996, Biometrics 52, 226-242), and the estimated models are compared with those obtained by Rathbun.     

Bayesian lasso for semiparametric structural equation models

There has been great interest in developing nonlinear structural equation models and associated statistical inference procedures, including estimation and model selection methods. In this paper a general semiparametric structural equation model (SSEM) is developed in which the structural equation is composed of nonparametric functions of exogenous latent variables and fixed covariates on a set of latent endogenous variables. A basis representation is used to approximate these nonparametric functions in the structural equation and the Bayesian Lasso method coupled with a Markov Chain Monte Carlo (MCMC) algorithm is used for simultaneous estimation and model selection. The proposed method is illustrated using a simulation study and data from the Affective Dynamics and Individual Differences (ADID) study. Results demonstrate that our method can accurately estimate the unknown parameters and correctly identify the true underlying model.     

Phase sensitivity analysis of circadian rhythm entrainment

As a biological clock, circadian rhythms evolve to accomplish a stable (robust) entrainment to environmental cycles, of which light is the most obvious. The mechanism of photic entrainment is not known, but two models of entrainment have been proposed based on whether light has a continuous (parametric) or discrete (nonparametric) effect on the circadian pacemaker. A novel sensitivity analysis is developed to study the circadian entrainment in silico based on a limit cycle approach and applied to a model of Drosophila circadian rhythm. The comparative analyses of complete and skeleton photoperiods suggest a trade-off between the contribution of period modulation (parametric effect) and phase shift (nonparametric effect) in Drosophila circadian entrainment. The results also give suggestions for an experimental study to (in)validate the two models of entrainment.     

Interspecific variation in tephritid fruit fly larvae surface hydrocarbons

Hydrocarbons extracted from seven species of tephritid fruit fly larvae were analyzed using capillary column gas-liquid chromatography and gas-liquid chromatography/mass spectrometry. Interspecific variation in hydrocarbon patterns was evaluated using both classical and nonparametric discriminant analysis for four of the seven Anastrepha taxa; A. acris, A. Fraterculus, A. suspensa and A. obliqua. Three of the four taxa, excluding A. acris, were correctly classified using a linear discriminant model at 72–83% and a nonparametric kernel density discriminant model at 87–92%. © 1993 Wiley-Liss. Inc.