Profile Likelihood Approach Research Articles

Profile-Likelihood Approach for Estimating Generalized Linear Mixed Models With Factor Structures

In this article, the authors suggest a profile-likelihood approach for estimating complex models by maximum likelihood (ML) using standard software and minimal programming. The method works whenever setting some of the parameters of the model to known constants turns the model into a standard model. An important class of models that can be estimated this way is generalized linear mixed models with factor structures. Such models are useful in educational research, for example, for estimation of value-added teacher or school effects with persistence parameters and for analysis of large-scale assessment data using multilevel item response models with discrimination parameters. The authors describe the profile-likelihood approach, implement it in the R software, and apply the method to longitudinal data and binary item response data. Simulation studies and comparison with gllamm show that the profile-likelihood method performs well in both types of applications. The authors also briefly discuss other types of models that can be estimated using the profile-likelihood idea.

Profile likelihood‐based confidence interval of the intraclass correlation for binary outcome data sampled from clusters

The intraclass correlation in binary outcome data sampled from clusters is an important and versatile measure in many biological and biomedical investigations. Properties of the different estimators of the intraclass correlation based on the parametric, semi-parametric, and nonparametric approaches have been studied extensively, mainly in terms of bias and efficiency [see, for example, Ridout et al., Biometrics 1999, 55:137-148; Paul et al., Journal of Statistical Computation and Simulation 2003, 73:507-523; and Lee, Statistical Modelling 2004, 4: 113-126], but little attention has been paid to extending these results to the problem of the confidence intervals. In this article, we generalize the results of the four point estimators by constructing asymptotic confidence intervals obtaining closed-form asymptotic and sandwich variance expressions of those four point estimators. It appears from simulation results that the asymptotic confidence intervals based on these four estimators have serious under-coverage. To remedy this, we introduce the Fisher's z-transformation approach on the intraclass correlation coefficient, the profile likelihood approach based on the beta-binomial model, and the hybrid profile variance approach based on the quadratic estimating equation for constructing the confidence intervals of the intraclass correlation for binary outcome data. As assessed by Monte Carlo simulations, these confidence interval approaches show significant improvement in the coverage probabilities. Moreover, the profile likelihood approach performs quite well by providing coverage levels close to nominal over a wide range of parameter combinations. We provide applications to biological data to illustrate the methods.

Profile likelihood-based confidence interval for the dispersion parameter in count data

The importance of the dispersion parameter in counts occurring in toxicology, biology, clinical medicine, epidemiology, and other similar studies is well known. A couple of procedures for the construction of confidence intervals (CIs) of the dispersion parameter have been investigated, but little attention has been paid to the accuracy of its CIs. In this paper, we introduce the profile likelihood (PL) approach and the hybrid profile variance (HPV) approach for constructing the CIs of the dispersion parameter for counts based on the negative binomial model. The non-parametric bootstrap (NPB) approach based on the maximum likelihood (ML) estimates of the dispersion parameter is also considered. We then compare our proposed approaches with an asymptotic approach based on the ML and the restricted ML (REML) estimates of the dispersion parameter as well as the parametric bootstrap (PB) approach based on the ML estimates of the dispersion parameter. As assessed by Monte Carlo simulations, the PL approach has the best small-sample performance, followed by the REML, HPV, NPB, and PB approaches. Three examples to biological count data are presented.

In silico labeling reveals the time-dependent label half-life and transit-time in dynamical systems

BackgroundMathematical models of dynamical systems facilitate the computation of characteristic properties that are not accessible experimentally. In cell biology, two main properties of interest are (1) the time-period a protein is accessible to other molecules in a certain state - its half-life - and (2) the time it spends when passing through a subsystem - its transit-time. We discuss two approaches to quantify the half-life, present the novel method of in silico labeling, and introduce the label half-life and label transit-time. The developed method has been motivated by laboratory tracer experiments. To investigate the kinetic properties and behavior of a substance of interest, we computationally label this species in order to track it throughout its life cycle. The corresponding mathematical model is extended by an additional set of reactions for the labeled species, avoiding any double-counting within closed circuits, correcting for the influences of upstream fluxes, and taking into account combinatorial multiplicity for complexes or reactions with several reactants or products. A profile likelihood approach is used to estimate confidence intervals on the label half-life and transit-time.ResultsApplication to the JAK-STAT signaling pathway in Epo-stimulated BaF3-EpoR cells enabled the calculation of the time-dependent label half-life and transit-time of STAT species. The results were robust against parameter uncertainties.ConclusionsOur approach renders possible the estimation of species and label half-lives and transit-times. It is applicable to large non-linear systems and an implementation is provided within the PottersWheel modeling framework (http://www.potterswheel.de).

A Median Regression Model to Estimate the Parameters of the Three-Parameter Generalized Pareto Distribution

A regression procedure to estimate the parameters of the three-parameter generalized Pareto distribution is derived. The distribution function is transformed to a linear regression model where the dependent variable is in the Box-Cox transformed form. The profile likelihood approach assuming Laplace distributed disturbances and weighted least squares are used to estimate the parameters. The regression approach performs good in small samples with respect to efficiency. Two applications to estimate the index in peak over threshold problems are given.

Semiparametric inference in a GARCH-in-mean model

A new semiparametric estimator for an empirical asset pricing model with general nonparametric risk-return tradeoff and GARCH-type underlying volatility is introduced. Based on the profile likelihood approach, it does not rely on any initial parametric estimator of the conditional mean function, and it is under stated conditions consistent, asymptotically normal, and efficient, i.e., it achieves the semiparametric lower bound. A sampling experiment provides finite sample comparisons with the parametric approach and the iterative semiparametric approach with parametric initial estimate of Conrad and Mammen (2008). An application to daily stock market returns suggests that the risk-return relation is indeed nonlinear.

Robust Discovery of Genetic Associations Incorporating Gene-Environment Interaction and Independence

This article considers the detection and evaluation of genetic effects incorporating gene-environment interaction and independence. Whereas ordinary logistic regression cannot exploit the assumption of gene-environment independence, the proposed approach makes explicit use of the independence assumption to improve estimation efficiency. This method, which uses both cases and controls, fits a constrained retrospective regression in which the genetic variant plays the role of the response variable, and the disease indicator and the environmental exposure are the independent variables. The regression model constrains the association of the environmental exposure with the genetic variant among the controls to be null, thus explicitly encoding the gene-environment independence assumption, which yields substantial gain in accuracy in the evaluation of genetic effects. The proposed retrospective regression approach has several advantages. It is easy to implement with standard software, and it readily accounts for multiple environmental exposures of a polytomous or of a continuous nature, while easily incorporating extraneous covariates. Unlike the profile likelihood approach of Chatterjee and Carroll (Biometrika. 2005;92:399-418), the proposed method does not require a model for the association of a polytomous or continuous exposure with the disease outcome, and, therefore, it is agnostic to the functional form of such a model and completely robust to its possible misspecification.

Semiparametric Trending Panel Data Models with Cross-Sectional Dependence

A semiparametric fixed effects model is introduced to describe the nonlinear trending phenomenon in panel data analysis and it allows for the cross-sectional dependence in both the regressors and the residuals. A semiparametric profile likelihood approach based on the first-stage local linear fitting is developed to estimate both the parameter vector and the time trend function. As both the time series length T and the cross-sectional size N tend to infinity simultaneously, the resulting semiparametric estimator of the parameter vector is asymptotically normal with an optimal rate of convergence. Meanwhile, an asymptotic distribution for the estimate of the nonlinear time trend function is also established with also an optimal rate of convergence. Two simulated examples are provided to illustrate the finite sample behavior of the proposed estimation method. In addition, the proposed model and estimation method is applied to the analysis of two sets of real data.

Nonparametric maximum likelihood analysis of clustered current status data with the gamma-frailty Cox model

The Cox model with frailties has been popular for regression analysis of clustered event time data under right censoring. However, due to the lack of reliable computation algorithms, the frailty Cox model has been rarely applied to clustered current status data, where the clustered event times are subject to a special type of interval censoring such that we only observe for each event time whether it exceeds an examination (censoring) time or not. Motivated by the cataract dataset from a cross-sectional study, where bivariate current status data were observed for the occurrence of cataracts in the right and left eyes of each study subject, we develop a very efficient and stable computation algorithm for nonparametric maximum likelihood estimation of gamma-frailty Cox models with clustered current status data. The algorithm proposed is based on a set of self-consistency equations and the contraction principle. A convenient profile-likelihood approach is proposed for variance estimation. Simulation and real data analysis exhibit the nice performance of our proposal.

Robust inference in generalized partially linear models

In many situations, data follow a generalized partly linear model in which the mean of the responses is modeled, through a link function, linearly on some covariates and nonparametrically on the remaining ones. A new class of robust estimates for the smooth function η , associated to the nonparametric component, and for the parameter β , related to the linear one, is defined. The robust estimators are based on a three-step procedure, where large values of the deviance or Pearson residuals are bounded through a score function. These estimators allow us to make easier inferences on the regression parameter β and also improve computationally those based on a robust profile likelihood approach. The resulting estimates of β turn out to be root- n consistent and asymptotically normally distributed. Besides, the empirical influence function allows us to study the sensitivity of the estimators to anomalous observations. A robust Wald test for the regression parameter is also provided. Through a Monte Carlo study, the performance of the robust estimators and the robust Wald test is compared with that of the classical ones.

Profile Likelihood and Incomplete Data

According to the law of likelihood, statistical evidence is represented by likelihood functions and its strength measured by likelihood ratios. This point of view has led to a likelihood paradigm for interpreting statistical evidence, which carefully distinguishes evidence about a parameter from error probabilities and personal belief. Like other paradigms of statistics, the likelihood paradigm faces challenges when data are observed incompletely, due to non-response or censoring, for instance. Standard methods to generate likelihood functions in such circumstances generally require assumptions about the mechanism that governs the incomplete observation of data, assumptions that usually rely on external information and cannot be validated with the observed data. Without reliable external information, the use of untestable assumptions driven by convenience could potentially compromise the interpretability of the resulting likelihood as an objective representation of the observed evidence. This paper proposes a profile likelihood approach for representing and interpreting statistical evidence with incomplete data without imposing untestable assumptions. The proposed approach is based on partial identification and is illustrated with several statistical problems involving missing data or censored data. Numerical examples based on real data are presented to demonstrate the feasibility of the approach.

Efficient semiparametric estimation in generalized partially linear additive models

In this paper we study semiparametric generalized additive models in which some part of the additive function is linear. We study the semiparametric efficiency under this regression model for the exponential family. We also present an asymptotically efficient estimation procedure based on the generalized profile likelihood approach.

Joint Modeling of Survival Data and Longitudinal Measurements Under Nested Case-Control Sampling

Nested case-control design is a popular epidemiological sampling method because it is cost effective for studying the temporal relationship between a disease and related risk factors. When there are repeated measures of the potential risk factor, the standard conditional logistic regression approach is no longer applicable. In this article, we propose a joint modeling approach for the survival times and the longitudinal measurements of the risk factor under the nested case-control sampling. We adopt the idea of shared latent parameters and present a maximum likelihood estimator (MLE) to evaluate the association between longitudinal exposure measurements and time to event. We employ the EM algorithm to carry out the maximum likelihood estimation and use an EM-aided profile likelihood approach to estimate the standard errors. Extensive simulations show the validity and efficiency of our method.

Mis-Specification Analysis of Linear Degradation Models

Degradation models are widely used to assess the lifetime information of highly reliable products if there exists quality characteristics whose degradation over time can be related to reliability. The performance of a degradation model depends strongly on the appropriateness of the model describing a product's degradation path. In this paper, motivated by laser data, we propose a general linear degradation path in which the unit-to-unit variation of all test units can be considered simultaneously with the time-dependent structure in degradation paths. Based on the proposed degradation model, we first derive an implicit expression of a product's lifetime distribution, and its corresponding mean-time-to-failure (MTTF). By using the profile likelihood approach, maximum likelihood estimation of parameters, a product's MTTF, and their confidence intervals can be obtained easily. In addition, laser degradation data are used to illustrate the proposed procedure. Furthermore, we also address the effects of model mis-specification on the prediction of the product's MTTF. It shows that the effect of the model mis-specification on the predictions of a product's MTTF is not critical under the case of large samples. However, when the sample size and the termination time are not large enough, a simulation study shows that these effects are not negligible.

Case-cohort analysis with semiparametric transformation models

Semiparametric transformation models provide flexible regression models for survival analysis, including the Cox proportional hazards and the proportional odds models as special cases. We consider the application of semiparametric transformation models in case-cohort studies, where the covariate data are observed only on cases and on a subcohort randomly sampled from the full cohort. We first propose an approximate profile likelihood approach with full-cohort data, which amounts to the pseudo-partial likelihood approach of Zucker [2005. A pseudo-partial likelihood method for semiparametric survival regression with covariate errors. J. Amer. Statist. Assoc. 100, 1264–1277]. Simulation results show that our proposal is almost as efficient as the nonparametric maximum likelihood estimator. We then extend this approach to the case-cohort design, applying the Horvitz–Thompson weighting method to the estimating equations from the approximated profile likelihood. Two levels of weights can be utilized to achieve unbiasedness and to gain efficiency. The resulting estimator has a closed-form asymptotic covariance matrix, and is found in simulations to be substantially more efficient than the estimator based on martingale estimating equations. The extension to left-truncated data will be discussed. We illustrate the proposed method on data from a cardiovascular risk factor study conducted in Taiwan.

Semi-parametric efficiency bounds for regression models under response-selective sampling: the profile likelihood approach

We obtain an information bound for estimates of parameters in general regression models where data are collected under a variety of response-selective sampling schemes, together with a simple formula for the asymptotic variance of the semi-parametric maximum likelihood estimate. This is compared to the bound and the estimate is found to be fully efficient in a variety of settings. A small simulation study is reported to illustrate the small-sample efficiency of the semi-parametric estimator.

Semiparametric Inference in a GARCH-in-Mean Model

A new semiparametric estimator for an empirical asset pricing model with general nonparametric risk-return tradeoff and a GARCH process for the underlying volatility is introduced. The estimator does not rely on any initial parametric estimator of the conditional mean function, and this feature facilitates the derivation of asymptotic theory under possible nonlinearity of unspecified form of the risk-return tradeoff. Besides the nonlinear GARCH-in-mean effect, our specification accommodates exogenous regressors that are typically used as conditioning variables entering linearly in the mean equation, such as the dividend yield. Using the profile likelihood approach, we show that our estimator under stated conditions is consistent, asymptotically normal, and efficient, i.e. it achieves the semiparametric lower bound. A sampling experiment provides evidence on finite sample properties as well as comparisons with the fully parametric approach and the iterative semiparametric approach using a parametric initial estimate proposed by Conrad and Mammen (2008). An empirical application to the daily S&P 500 stock market returns suggests that the linear relation between conditional expected return and conditional variance of returns from the literature is misspecified, and this could be the reason for the disagreement on the sign of the relation.

Constrained local likelihood estimators for semiparametric skew-normal distributions

SUMMARY A local likelihood estimator for a nonparametric nuisance function is proposed in the context of semiparametric skew-normal distributions. Constraints imposed on such functions result in a nonparametric estimator with a different target function for maximization from classical local likelihood estimators. The optimal asymptotic semiparametric efficiency bound on parameters of interest is achieved by using this estimator in conjunction with an estimating equation formed by summing efficient scores. A generalized profile likelihood approach is also proposed. This method has the advantage of providing a unique estimate in cases where an estimating equation has multiple solutions. Our nonparametric estimator of the nuisance function leads to an estimator of the semiparametric skew-normal density. Both the estimating equation and profile likelihood approaches are applicable to more general skew-symmetric distributions.

Supervised Detection of Conserved Motifs in DNA Sequences with Cosmo

A number of computational methods have been proposed for identifying transcription factor binding sites from a set of unaligned sequences that are thought to share the motif in question. We here introduce an algorithm, called cosmo, that allows this search to be supervised by specifying a set of constraints that the position weight matrix of the unknown motif must satisfy. Such constraints may be formulated, for example, on the basis of prior knowledge about the structure of the transcription factor in question. The algorithm is based on the same two-component multinomial mixture model used by MEME, with stronger reliance, however, on the likelihood principle instead of more ad-hoc criteria like the E-value. The intensity parameter in the ZOOPS and TCM models, for instance, is estimated based on a profile-likelihood approach, and the width of the unknown motif is selected based on BIC. These changes allow cosmo to outperform MEME even in the absence of any constraints, as evidenced by 2- to 3-fold greater sensitivity in some simulation studies. Additional improvements in performance can be achieved by selecting the model type (OOPS, ZOOPS, or TCM) data-adaptively or by supplying correctly specified constraints, especially if the motif appears only as a weak signal in the data. The algorithm can data-adaptively choose between working in a given constrained model or in the completely unconstrained model, guarding against the risk of supplying mis-specified constraints. Simulation studies suggest that this approach can offer 3 to 3.5 times greater sensitivity than MEME. The algorithm has been implemented in the form of a stand-alone C program as well as a web application that can be accessed at http://cosmoweb.berkeley.edu. An R package is available through Bioconductor (http://bioconductor.org).

Inference for Log-Gamma Distribution Based on Progressively Type-II Censored Data

We discuss the maximum likelihood estimates (MLEs) of the parameters of the log-gamma distribution based on progressively Type-II censored samples. We use the profile likelihood approach to tackle the problem of the estimation of the shape parameter κ. We derive approximate maximum likelihood estimators of the parameters μ and σ and use them as initial values in the determination of the MLEs through the Newton–Raphson method. Next, we discuss the EM algorithm and propose a modified EM algorithm for the determination of the MLEs. A simulation study is conducted to evaluate the bias and mean square error of these estimators and examine their behavior as the progressive censoring scheme and the shape parameter vary. We also discuss the interval estimation of the parameters μ and σ and show that the intervals based on the asymptotic normality of MLEs have very poor probability coverages for small values of m. Finally, we present two examples to illustrate all the methods of inference discussed in this paper.