Models for longitudinal data with censored changepoints

Summary.  In longitudinal studies of biological markers, different individuals may have different underlying patterns of response. In some applications, a subset of individuals experiences latent events, causing an instantaneous change in the level or slope of the marker trajectory. The paper presents a general mixture of hierarchical longitudinal models for serial biomarkers. Interest centres both on the time of the event and on levels of the biomarker before and after the event. In observational studies where marker series are incomplete, the latent event can be modelled by a survival distribution. Risk factors for the occurrence of the event can be investigated by including covariates in the survival distribution. A combination of Gibbs, Metropolis–Hastings and reversible jump Markov chain Monte Carlo sampling is used to fit the models to serial measurements of forced expiratory volume from lung transplant recipients.     

On-line monitoring data quality of high-dimensional data streams

ABSTRACT

In recent years, effective monitoring of data quality has increasingly attracted attention of researchers in the area of statistical process control. Among the relevant research on this topic, none used multivariate methods to control the multidimensional data quality process, but instead relied on multiple univariate control charts. Based on a novel one-sided multivariate exponentially weighted moving average (MEWMA) chart, we propose a conditional false discovery rate-adjusted scheme to on-line monitor the data quality of high-dimensional data streams. With thousands of input data streams, the average run length loses its usefulness because one will likely have out-of-control signals at each time period. Hence, we first control the percentage of signals that are false alarms. Then, we compare the power of the proposed MEWMA scheme with that of two alternative methods. Compared with two competitors, numerical results show that the proposed MEWMA scheme has higher average power.     

Spatial prediction and spatial dependence monitoring on georeferenced data streams

Statistical Methods & Applications - This paper deals with the analysis of data streams recorded by georeferenced sensors. We focus on the problem of measuring the spatial dependence among the...     

Alternative beta estimation for the market model using partially adaptive techniques

The leptokurtosls of many security market return distributions can contaminate ordinary least squares estimates of the β coefficient of the market model. Partially adaptive estimation techniques accommodate the possibility of fat tailed distributions. this methodology limits the influence of extremely large residuals and yields estimates which are both statistically and practically different from ordinary least squares.     

Pharmacokinetic parameters estimation using adaptive Bayesian P-splines models

In preclinical and clinical experiments, pharmacokinetic (PK) studies are designed to analyse the evolution of drug concentration in plasma over time i.e. the PK profile. Some PK parameters are estimated in order to summarize the complete drug's kinetic profile: area under the curve (AUC), maximal concentration (C(max)), time at which the maximal concentration occurs (t(max)) and half-life time (t(1/2)).Several methods have been proposed to estimate these PK parameters. A first method relies on interpolating between observed concentrations. The interpolation method is often chosen linear. This method is simple and fast. Another method relies on compartmental modelling. In this case, nonlinear methods are used to estimate parameters of a chosen compartmental model. This method provides generally good results. However, if the data are sparse and noisy, two difficulties can arise with this method. The first one is related to the choice of the suitable compartmental model given the small number of data available in preclinical experiment for instance. Second, nonlinear methods can fail to converge. Much work has been done recently to circumvent these problems (J. Pharmacokinet. Pharmacodyn. 2007; 34:229-249, Stat. Comput., to appear, Biometrical J., to appear, ESAIM P&S 2004; 8:115-131).In this paper, we propose a Bayesian nonparametric model based on P-splines. This method provides good PK parameters estimation, whatever be the number of available observations and the level of noise in the data. Simulations show that the proposed method provides better PK parameters estimations than the interpolation method, both in terms of bias and precision. The Bayesian nonparametric method provides also better AUC and t(1/2) estimations than a correctly specified compartmental model, whereas this last method performs better in t(max) and C(max) estimations.We extend the basic model to a hierarchical one that treats the case where we have concentrations from different subjects. We are then able to get individual PK parameter estimations. Finally, with Bayesian methods, we can get easily some uncertainty measures by obtaining credibility sets for each PK parameter.     

Incremental modelling for compositional data streams

ABSTRACT

Incremental modelling of data streams is of great practical importance, as shown by its applications in advertising and financial data analysis. We propose two incremental covariance matrix decomposition methods for a compositional data type. The first method, exact incremental covariance decomposition of compositional data (C-EICD), gives an exact decomposition result. The second method, covariance-free incremental covariance decomposition of compositional data (C-CICD), is an approximate algorithm that can efficiently compute high-dimensional cases. Based on these two methods, many frequently used compositional statistical models can be incrementally calculated. We take multiple linear regression and principle component analysis as examples to illustrate the utility of the proposed methods via extensive simulation studies.     

Online monitoring of high-dimensional binary data streams with application to extreme weather surveillance

With the rapid development of modern sensor technology, high-dimensional data streams appear frequently nowadays, bringing urgent needs for effective statistical process control (SPC) tools. In such a context, the online monitoring problem of high-dimensional and correlated binary data streams is becoming very important. Conventional SPC methods for monitoring multivariate binary processes may fail when facing high-dimensional applications due to high computational complexity and the lack of efficiency. In this paper, motivated by an application in extreme weather surveillance, we propose a novel pairwise approach that considers the most informative pairwise correlation between any two data streams. The information is then integrated into an exponential weighted moving average (EWMA) charting scheme to monitor abnormal mean changes in high-dimensional binary data streams. Extensive simulation study together with a real-data analysis demonstrates the efficiency and applicability of the proposed control chart.     

Hierarchical Bayes estimation in small area estimation using cross-sectional and time-series data

Bayesian methods have been extensively used in small area estimation. A linear model incorporating autocorrelated random effects and sampling errors was previously proposed in small area estimation using both cross-sectional and time-series data in the Bayesian paradigm. There are, however, many situations that we have time-related counts or proportions in small area estimation; for example, monthly dataset on the number of incidence in small areas. This article considers hierarchical Bayes generalized linear models for a unified analysis of both discrete and continuous data with incorporating cross-sectional and time-series data. The performance of the proposed approach is evaluated through several simulation studies and also by a real dataset.     

Parameter estimation for the dirichlet-multinomial distribution using supplementary beta-binomial data

We develop estimates for the parameters of the Dirichlet-multinomial distribution (DMD) when there is insufficient data to obtain maximum likelihood or method of moment estimates known in the literature. We do, however, have supplemetary beta-binomial data pertaining to the marginals of the DMD, and use these data when estimating the DMD parameters. A real situation and data set are given where our estimates are applicable.     

Tail density estimation for exploratory data analysis using kernel methods

It is often critical to accurately model the upper tail behaviour of a random process. Nonparametric density estimation methods are commonly implemented as exploratory data analysis techniques for this purpose and can avoid model specification biases implied by using parametric estimators. In particular, kernel-based estimators place minimal assumptions on the data, and provide improved visualisation over scatterplots and histograms. However kernel density estimators can perform poorly when estimating tail behaviour above a threshold, and can over-emphasise bumps in the density for heavy tailed data. We develop a transformation kernel density estimator which is able to handle heavy tailed and bounded data, and is robust to threshold choice. We derive closed form expressions for its asymptotic bias and variance, which demonstrate its good performance in the tail region. Finite sample performance is illustrated in numerical studies, and in an expanded analysis of the performance of global climate models.     

Nonparametric estimation in the illness-death model using prevalent data

We study nonparametric estimation of the illness-death model using left-truncated and right-censored data. The general aim is to estimate the multivariate distribution of a progressive multi-state process. Maximum likelihood estimation under censoring suffers from problems of uniqueness and consistency, so instead we review and extend methods that are based on inverse probability weighting. For univariate left-truncated and right-censored data, nonparametric maximum likelihood estimation can be considerably improved when exploiting knowledge on the truncation distribution. We aim to examine the gain in using such knowledge for inverse probability weighting estimators in the illness-death framework. Additionally, we compare the weights that use truncation variables with the weights that integrate them out, showing, by simulation, that the latter performs more stably and efficiently. We apply the methods to intensive care units data collected in a cross-sectional design, and discuss how the estimators can be easily modified to more general multi-state models.     

Bayesian population estimation for small sample capture-recapture data using noninformative priors

One critical issue in the Bayesian approach is choosing the priors when there is not enough prior information to specify hyperparameters. Several improper noninformative priors for capture-recapture models were proposed in the literature. It is known that the Bayesian estimate can be sensitive to the choice of priors, especially when sample size is small to moderate. Yet, how to choose a noninformative prior for a given model remains a question. In this paper, as the first step, we consider the problem of estimating the population size for _Mt$M_{\mathrm{t}}$ model using noninformative priors. The _Mt$M_{\mathrm{t}}$ model has prodigious application in wildlife management, ecology, software liability, epidemiological study, census under-count, and other research areas. Four commonly used noninformative priors are considered. We find that the choice of noninformative priors depends on the number of sampling occasions only. The guidelines on the choice of noninformative priors are provided based on the simulation results. Propriety of applying improper noninformative prior is discussed. Simulation studies are developed to inspect the frequentist performance of Bayesian point and interval estimates with different noninformative priors under various population sizes, capture probabilities, and the number of sampling occasions. The simulation results show that the Bayesian approach can provide more accurate estimates of the population size than the MLE for small samples. Two real-data examples are given to illustrate the method.     

An adaptive resampling scheme for cycle estimation

Bayesian dynamic linear models (DLMs) are useful in time series modelling, because of the flexibility that they off er for obtaining a good forecast. They are based on a decomposition of the relevant factors which explain the behaviour of the series through a series of state parameters. Nevertheless, the DLM as developed by West and Harrison depend on additional quantities, such as the variance of the system disturbances, which, in practice, are unknown. These are referred to here as 'hyper-parameters' of the model. In this paper, DLMs with autoregressive components are used to describe time series that show cyclic behaviour. The marginal posterior distribution for state parameters can be obtained by weighting the conditional distribution of state parameters by the marginal distribution of hyper-parameters. In most cases, the joint distribution of the hyperparameters can be obtained analytically but the marginal distributions of the components cannot, so requiring numerical integration. We propose to obtain samples of the hyperparameters by a variant of the sampling importance resampling method. A few applications are shown with simulated and real data sets.     

Density and hazard rate estimation for right-censored data by using wavelet methods

This paper describes a wavelet method for the estimation of density and hazard rate functions from randomly right-censored data. We adopt a nonparametric approach in assuming that the density and hazard rate have no specific parametric form. The method is based on dividing the time axis into a dyadic number of intervals and then counting the number of events within each interval. The number of events and the survival function of the observations are then separately smoothed over time via linear wavelet smoothers, and then the hazard rate function estimators are obtained by taking the ratio. We prove that the estimators have pointwise and global mean-square consistency, obtain the best possible asymptotic mean integrated squared error convergence rate and are also asymptotically normally distributed. We also describe simulation experiments that show that these estimators are reasonably reliable in practice. The method is illustrated with two real examples. The first uses survival time data for patients with liver metastases from a colorectal primary tumour without other distant metastases. The second is concerned with times of unemployment for women and the wavelet estimate, through its flexibility, provides a new and interesting interpretation.     

A new adaptive EWMA control chart using auxiliary information for monitoring the process mean

The adaptive memory-type control charts, including the adaptive exponentially weighted moving average (EWMA) and cumulative sum (CUSUM) charts, have gained considerable attention because of their excellent speed in providing overall good detection over a range of mean shift sizes. In this paper, we propose a new adaptive EWMA (AEWMA) chart using the auxiliary information for efficiently monitoring the infrequent changes in the process mean. The idea is to first estimate the unknown process mean shift using an auxiliary information based mean estimator, and then adaptively update the smoothing constant of the EWMA chart. Using extensive Monte Carlo simulations, the run length profiles of the AEWMA chart are computed and explored. The AEWMA chart is compared with the existing control charts, including the classical EWMA, CUSUM, synthetic EWMA and synthetic CUSUM charts, in terms of the run length characteristics. It turns out that the AEWMA chart performs uniformly better than these control charts when detecting a range of mean shift sizes. An illustrative example is also presented to demonstrate the working and implementation of the proposed and existing control charts.     

Optimal smoothing in adaptive location estimation

In this paper, we consider higher order performance of kernel based adaptive location estimates. We show how much one loses in efficiency without knowing the underlying translation density, and derive the optimal order of the bandwidths involved in kernel estimation of the efficient score function. The optimal order is obtained by minimizing the loss of efficiency in terms of estimating the location parameter. The main lesson here is that the optimal order of the bandwidths are different from those for optimal estimation of the score function. This implies that optimal estimation of the score function does not lead to second order optimal location estimation.     

Variance estimation in adaptive cluster sampling

Abstract

In this paper, a class of variance estimator is proposed of a finite population variance under an adaptive cluster sampling design in the presence of information on an auxiliary variable. We obtain expressions for the mean square error and bias for the developed estimators and their performance is evaluated on a Poisson clustered process and a real data set. The simulation study evaluates the efficiency of the suggested estimators for an adaptive cluster sampling (ACS) design and the Isaki (1983 Isaki, C. T. 1983. Variance estimation using auxiliary information. Journal of the American Statistical Association 78 (381):117–23. doi: 10.1080/01621459.1983.10477939.[Taylor & Francis Online], [Web of Science ®] , [Google Scholar]) estimator of the variance for SRSWOR over the sample variance for SRSWOR.     

Frontier estimation using kernel smoothing estimators with data transformation

In economics, a production frontier function is a graph that shows the maximum output of production units such as firms, industries, or economies, as a function of their inputs. Practically, estimating production frontiers often requires imposition of constraints such as monotonicity or monotone concavity. However, few constrained estimators of production frontier have been proposed in the literature. They are based on simple envelopment techniques which often suffer from lack of precision and smoothness. Motivated by this observation, we propose a smooth constrained nonparametric frontier estimator respecting constraints by considering kernel smoothing estimators from a transformed data. It is particularly appealing to practitioners who would like to use smooth estimates that, in addition, satisfy theoretical axioms of production. The utility of this method is illustrated through application to one real dataset and simulation evidences are also presented to show its superiority over the most known methods.     

Uniformly adaptive estimation for models with arma errors

A semiparametric estimator based on an unknown density isuniformly adaptive if the expected loss of the estimator converges to the asymptotic expected loss of the maximum liklihood estimator based on teh true density (MLE), and if convergence does not depend on either the parameter values or the form of the unknown density. Without uniform adaptivity, the asymptotic expected loss of the MLE need not approximate the expected loss of a semiparametric estimator for any finite sample I show that a two step semiparametric estimator is uniformly adaptive for the parameters of nonlinear regression models with autoregressive moving average errors.