Modeling clustered, discrete, or grouped time survival data with covariates

We have developed methods for modeling discrete or grouped time, right-censored survival data collected from correlated groups or clusters. We assume that the marginal hazard of failure for individual items within a cluster is specified by a linear log odds survival model and the dependence structure is based on a gamma frailty model. The dependence can be modeled as a function of cluster-level covariates. Likelihood equations for estimating the model parameters are provided. Generalized estimating equations for the marginal hazard regression parameters and pseudolikelihood methods for estimating the dependence parameters are also described. Data from two clinical trials are used for illustration purposes.     

Distribution-free regression analysis of grouped survival data

Methods based on regression models for logarithmic hazard functions, Cox models, are given for analysis of grouped and censored survival data. By making an approximation it is possible to obtain explicitly a maximum likelihood function involving only the regression parameters. This likelihood function is a convenient analog to Cox's partial likelihood for ungrouped data. The method is applied to data from a toxicological experiment.     

A Model for Censored Survival Data When There is an Intervening Event

A model is discussed for incorporating information from a time-dependent covariable (an intervening event) and covariables independent of time into the analysis of survival data. In the model, it is assumed that individuals are potentially subject to two paths to failure, one including the intervening event and the other not. Additional assumptions are that failure times associated with the two paths are independent and that the time to failure subsequent to the intervening event is dependent on the intervening event time. Allowing the underlying hazard rates for the model to follow a WEIBULL form, use of the model and methods for fitting and hypothesis testing are illustrated by application to a follow-up study involving industrial workers where disability retirement was the intervening event. Extensions of the model to accommodate grouped survival data are presented.     

城市建成区土地利用的环境影响评价——以南昌市主城区为例

基于土地利用环境影响的相关研究和城市土地利用特点,构建了城市建成区土地利用环境影响评价的概念模型,将建成区土地利用环境影响评价总结为细化、抽象、对应和评价4个基本过程,并以南昌市主城区为研究对象,分析了该区噪声、气味、粉尘和危险4个因素对环境的影响.结果表明：研究区噪声的影响范围占研究区总面积的59%;气味和粉尘的影响主要集中在主城区的东部和南部地区;危险的影响范围主要集中在主城区的东南方向,是南昌市工业较集中的区域,影响面积达19.6 km².该模型将城市建成区环境影响评价分为4个基本过程是可行的,可为研究区土地管理、城市规划等相关政策的制定提供依据.     

Maximum likelihood estimation for a special type of grouped data with an application to a dose-response problem.

A short-cut method is given for calculating grouped maximum likelihood (ML) estimates when the data are relatively coarsely grouped in some directions, but more finely grouped in others. The algebraic details are then worked out for a dose-response problem that generates data of this kind. The situation envisaged is a variation on the usual quantal response problem in that dosage levels are taken to be random but grouped. Finally, the method is applied both to real and simulated response data conforming to this pattern and shown to work well in practice.     

Semiparametric estimation of random effects using the Cox model based on the EM algorithm.

Consider a survival experiment where individuals within a certain subset of the population share a common, unobservable, random frailty. Such a frailty could be an unobservable genetic or early environmental effect if individuals were in sibling groups or an environmental effect if individuals were grouped by households. Suppose that if the frailty, omega, is known, the Cox proportional hazards model for the observable covariates is valid with the consequence of the random effect being a multiplicative factor on the hazard rate. Assuming tht the random frailties follow a gamma distribution, estimates of the fixed and random effects are obtained by using an EM algorithm based on a profile likelihood construction. The method developed is applied to the Framingham Heart Study to examine the risks of smoking and cholesterol levels, adjusting for potential random effects.     

Mitigation of ruminant methane production: current strategies,constraints and future options

Mitigating methane losses from cattle has economic as well as environmental benefits. The aim of this paper is to review the current approaches in relation to associated advantages and disadvantages and future options to reduce enteric methane emission from cattle. Current technologies can be broadly grouped into those that increase productivity of the animal (improved nutrition strategies) so that less methane is produced per unit of meat or milk, and those that directly modify the rumen fermentation so that less methane is produced in total. Data suggest that many of these practices are not appropriate for long term mitigation of methane emissions in ruminants because of their constraints. So it is necessity to develop long term strategies in suppressing methane production. An integrated research investigating animal, plant, microbe and nutrient level strategies would offer a long term solution of methane production. Genetic selection of animals, vaccination, probiotics, prebiotics and plant improvement are the most promising options of all the future approaches discussed. These approaches will reduce enteric methane production without any hazard to animal or environment.     

A nonparametric method for classification trees using grouped covariates

A group of variables are commonly seen in diagnostic medicine when multiple prognostic factors are aggregated into a composite score to represent the risk profile. A model selection method considers these covariates as all-in or all-out types. Model selection procedures for grouped covariates and their applications have thrived in recent years, in part because of the development of genetic research in which gene–gene or gene–environment interactions and regulatory network pathways are considered groups of individual variables. However, little has been discussed on how to utilize grouped covariates to grow a classification tree. In this paper, we propose a nonparametric method to address the selection of split variables for grouped covariates and their following selection of split points. Comprehensive simulations were implemented to show the superiority of our procedures compared to a commonly used recursive partition algorithm. The practical use of our method is demonstrated through a real data analysis that uses a group of prognostic factors to classify the successful mobilization of peripheral blood stem cells.     

Hazard function for cancer patients and cancer cell dynamics

The aim of the paper is to develop a procedure for an estimate of an analytical form of a hazard function for cancer patients. Although a deterministic approach based on cancer cell population dynamics yields the analytical expression, it depends on several parameters which should be estimated. On the other hand, a kernel estimate is an effective nonparametric method for estimating hazard functions. This method provides the pointwise estimate of the hazard function. Our procedure consists of two steps: in the first step we find the kernel estimate of the hazard function and in the second step the parameters in the deterministic model are obtained by the least squares method. A simulation study with different types of censorship is carried out and the developed procedure is applied to real data.     

Measures of Departure from Constant Failure Rate Models and Proportional Hazards Rate Models for Grouped Data

Two measures are proposed to represent the degree of departure from the constant failure rate model of a system when data are grouped. Two measures are also proposed to represent the degree of departure from the proportional hazards rate model when two systems are present and grouped data are considered. In each case one measure is based on the Kullback-Leibler discrepancy and the other is based on the Pearson χ² type discrepancy using the failure rates. The usefulness of the proposed measures are discussed with applications. A simulation study shows that the proposed measures perform no worse than the goodness-of-fit tests when testing for the constant failure rate model.     

Intermittent stimulation and delay of puberty by urinary chemosignals and social contact in wild stock female house mice (Mus Domesticus)

A sequence of six experiments using wild stock house mouse (Mus domesticus) tested the effects of intermittent stimulation with either the urinary chemosignal released by grouped female mice or social contact from grouped females on the age of first vaginal oestrus in young females. Weanling female mice were exposed to bedding soiled by grouped females or cages containing grouped females for 15 min periods, then removed for a prescribed period, and placed again in a cage with soiled bedding or grouped females. The nature of the exposure to the puberty delaying effect, the number of total exposures each day, the total length of exposure to the stimulus, and the total time period over which the exposures occurred were varied. None of the treatment regimes employed here with soiled bedding from grouped females resulted in delays in the onset of first oestrus in test females. Young females exposed to grouped females for 6 or 8 exposures in a 4 h period, 6 or 8 exposures in an 8 h period, or 8 exposures in a 12 h period were significantly delayed in attaining puberty relative to control females that were exposed to cages containing clean bedding. These results are in contrast to earlier findings involving chemosignals that accelerate first oestrus wherein young females exhibited the capacity to accumulate the exposures to the urinary chemosignals from males, females in oestrus and pregnant or lactating females. Direct exposure to the grouped females on an intermittent basis can provide stimulation that is cummulative and results in delays in the onset of first oestrus.     

In silico analysis of lactic acid secretion metabolism through the top-down approach: Effect of grouping in enzyme kinetics

A top-down approach is known to be a useful and effective technique for the design and analysis of metabolic systems. In this study, we have constructed a grouped metabolic network forLactococcus lactis under aerobic conditions using grouped enzyme kinetics. To test the usefulness of grouping work, a non-grouped system and grouped systems were compared quantitatively with each other. Here, grouped systems were designed as two groups according to the extent of grouping. The overall simulated flux values in grouped and non-grouped models had pretty similar distribution trends, but the details on flux ratio at the pyruvate branch point showed a little difference. This result indicates that our grouping technique can be used as a good model for complicated metabolic networks, however, for detailed analysis of metabolic network, a more robust mechanism should be considered. In addition to the data for the pyruvate branch point analysis, some major flux control coefficients were obtained in this research.     

A theoretical basis for conditional probability analyses of neural discharge activity

A theory has been developed which allows the estimation of the probability density of a discharge, given that an arbitrary condition is fulfilled. It is shown that the common methods for the evaluation of a post-stimulus time (PST) histogram and a hazard function can be considered as special applications of this theory. Whereas the usual hazard function shows how the probability of a discharge depends on the time elapsed since the last discharge, generalized hazard functions proposed in the present paper allow to reveal also the influence of the last but one discharge, the last but two discharge, and so on. In contrast to the usual method for the estimation of a hazard function, the applicability of the procedures proposed here is not restricted to stationary discharge activity. Some elementary applications are illustrated by analysing simulated discharge activity mimicing the response of a single auditory-nerve fiber to a high-intensity tone burst.     

Estimating the hazard of chemical substances to aquatic life

The assessment of the hazard associated with the introduction of chemical substances into the environment is receiving considerable attention in current ecological, political, and public forums. The purpose of this paper is to identify and evaluate the basic concepts involved in assessing the hazard of chemical substances to aquatic life. A conceptual framework for conducting a hazard assessment is elaborated. In addition, several proposed procedures for conducting aquatic hazard assessment are compared and contrasted. A discussion of the decision criteria currently utilized in hazard assessment procedures is included. The use of safety factors or uncertainty factors as a central concept in a sequential testing approach is presented. An assessment of the state-of-the-art in aquatic hazard assessment and recommendations for suceeding stpes in the development of procedures constitute the conclusion of the paper.     

Composite Hazard Functions Reflecting Competing Latent Processes

A method for fitting parametric models to apparently complex hazard rates in survival data is suggested. Hazard complexity may indicate competing causes of failure. A competing risks model is constructed on the assumption that a failure time can be considered as the first passage time of possibly several latent, stochastic processes competing in reaching a barrier. An additional assumption of independence between the hidden processes leads directly to a composite hazard function as the sum of the cause specific hazards. We show how this composite hazard model based on Wiener processes can serve as a flexible tool for modelling complex hazards by varying the number of processes and their starting conditions. An example with real data is presented. Parameter estimation and model assessment are based on Markov Chain Monte Carlo methods. (© 2004 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

Multivariate Bayesian analysis of Gaussian,right censored Gaussian,ordered categorical and binary traits using Gibbs sampling

A fully Bayesian analysis using Gibbs sampling and data augmentation in a multivariate model of Gaussian, right censored, and grouped Gaussian traits is described. The grouped Gaussian traits are either ordered categorical traits (with more than two categories) or binary traits, where the grouping is determined via thresholds on the underlying Gaussian scale, the liability scale. Allowances are made for unequal models, unknown covariance matrices and missing data. Having outlined the theory, strategies for implementation are reviewed. These include joint sampling of location parameters; efficient sampling from the fully conditional posterior distribution of augmented data, a multivariate truncated normal distribution; and sampling from the conditional inverse Wishart distribution, the fully conditional posterior distribution of the residual covariance matrix. Finally, a simulated dataset was analysed to illustrate the methodology. This paper concentrates on a model where residuals associated with liabilities of the binary traits are assumed to be independent. A Bayesian analysis using Gibbs sampling is outlined for the model where this assumption is relaxed.     

Regression with frailty in survival analysis

In studies of survival, the hazard function for each individual may depend on observed risk variables but usually not all such variables are known or measurable. This unknown factor of the hazard function is usually termed the individual heterogeneity or frailty. When survival is time to the occurrence of a particular type of event and more than one such time may be obtained for each individual, frailty is a common factor among such recurrence times. A model including frailty is fitted to such repeated measures of recurrence times.     

How to take a history of head or facial pain

A sequence of 15 questions is used to analyse pain, headache and facial pain being used for illustration. The questions are grouped for ease of memory—time, site, influencing and other factors—and arranged in such an order that simple questions are posed first.     

Mixture Hazard Models for Lifetime Data

We propose a general family of mixture hazard models to analyze lifetime data associated with bathtub and multimodal hazard functions. With this model we have a great flexibility for fitting lifetime data. Its version with covariates has the proportional hazard and the accelerated failure time models as special cases. A Bayesian analysis is presented for the model using informative priors, using sampling‐based approaches to perform the Bayesian computations. A real example with a medical data illustrates the methodology.     

Serological studies of ungroupable Neisseria meningitidis

Verification that Slaterus' Neisseria meningitidis serotypes X, Y, and Z are groups distinct from each other and from groups A, B, C, and D was made by use of the tube agglutination test on absorbed and unabsorbed antisera. A significant number of meningococcal strains in this country, which could not be classified serologically with standard antisera prepared to Branham's neotype A, B, C, and D strains, were grouped specifically with antisera prepared to the Slaterus types. The strains grouped as X, Y, and Z were from various geographical areas of the United States and were isolated from both carriers and cases. Over a 2-year period, the cultures tested ranged in predominance in descending order as follows: group B, C, Y, X, Z, A, and D. It is recommended that Slaterus' types should be considered as standard groups and follow in alphabetical order with the standard A, B, C, and D groups; i.e., X would be designated as group E, Y as group F, and Z as group G. It was observed that false-grouping cross-reactions could be greatly reduced by reconstituting the lyophilized grouping antisera in 50% glycerol-water. Of 99 cultures which could not be specifically grouped with antisera reconstituted in distilled water, 19 were specifically grouped with antisera reconstituted in 50% glycerol-water.