A zero-augmented gamma mixed model for longitudinal data with many zeros

In many occupational safety interventions, the objective is to reduce the injury incidence as well as the mean claims cost once injury has occurred. The claims cost data within a period typically contain a large proportion of zero observations (no claim). The distribution thus comprises a point mass at 0 mixed with a non-degenerate parametric component. Essentially, the likelihood function can be factorized into two orthogonal components. These two components relate respectively to the effect of covariates on the incidence of claims and the magnitude of claims, given that claims are made. Furthermore, the longitudinal nature of the intervention inherently imposes some correlation among the observations. This paper introduces a zero-augmented gamma random effects model for analysing longitudinal data with many zeros. Adopting the generalized linear mixed model (GLMM) approach reduces the original problem to the fitting of two independent GLMMs. The method is applied to evaluate the effectiveness of a workplace risk assessment teams program, trialled within the cleaning services of a Western Australian public hospital.

Long-term survivor mixture model with random effects: application to a multi-centre clinical trial of carcinoma

A mixture model incorporating long-term survivors has been adopted in the field of biostatistics where some individuals may never experience the failure event under study. The surviving fractions may be considered as cured. In most applications, the survival times are assumed to be independent. However, when the survival data are obtained from a multi-centre clinical trial, it is conceived that the environ mental conditions and facilities shared within clinic affects the proportion cured as well as the failure risk for the uncured individuals. It necessitates a long-term survivor mixture model with random effects. In this paper, the long-term survivor mixture model is extended for the analysis of multivariate failure time data using the generalized linear mixed model (GLMM) approach. The proposed model is applied to analyse a numerical data set from a multi-centre clinical trial of carcinoma as an illustration. Some simulation experiments are performed to assess the applicability of the model based on the average biases of the estimates formed. Copyright (C) 2001 John Wiley & Sons, Ltd.

Modelling inpatient length of stay by a hierarchical mixture regression via the EM algorithm

The modelling of inpatient length of stay (LOS) has important implications in health care studies. Finite mixture distributions are usually used to model the heterogeneous LOS distribution, due to a certain proportion of patients sustaining-a longer stay. However, the morbidity data are collected from hospitals, observations clustered within the same hospital are often correlated. The generalized linear mixed model approach is adopted to accommodate the inherent correlation via unobservable random effects. An EM algorithm is developed to obtain residual maximum quasi-likelihood estimation. The proposed hierarchical mixture regression approach enables the identification and assessment of factors influencing the long-stay proportion and the LOS for the long-stay patient subgroup. A neonatal LOS data set is used for illustration, (C) 2003 Elsevier Science Ltd. All rights reserved.

Feeding ecology of the fish ectoparasite Gnathia sp. (Crustacea: Isopoda) from the Great Barrier Reef, and its implications for fish cleaning behaviour

The feeding rate of a parasitic gnathiid isopod on fish was examined. Individual fish, Hemigymnus melapterus, were exposed to gnathiid larvae and sampled after 5, 10, 30, 60, and 240 min. I recorded whether larvae had an engorged gut, an engorged gut containing red material, or had dropped off the fish after having completed engorgement; variation among sampling times and larval stages was analyzed using generalized linear mixed model analyses. The likelihood that larvae had an engorged gut increased with time and varied with larval stage. First stage (1.45 mm) larvae. After 30 min, however, most (>93%) larvae had an engorged gut regardless of their larval stage. The likelihood of red material in the gut of third stage larvae increased over time (46% after 30 min, 70% after 60 min, and 86% after 240 min) while that of first and second stage larvae remained relatively low (

Designs for generalized linear models with several variables and model uncertainty

Standard factorial designs sometimes may be inadequate for experiments that aim to estimate a generalized linear model, for example, for describing a binary response in terms of several variables. A method is proposed for finding exact designs for such experiments that uses a criterion allowing for uncertainty in the link function, the linear predictor, or the model parameters, together with a design search. Designs are assessed and compared by simulation of the distribution of efficiencies relative to locally optimal designs over a space of possible models. Exact designs are investigated for two applications, and their advantages over factorial and central composite designs are demonstrated.

A Bayesian hierarchical model for categorical longitudinal data from a social survey of immigrants

The paper investigates a Bayesian hierarchical model for the analysis of categorical longitudinal data from a large social survey of immigrants to Australia. Data for each subject are observed on three separate occasions, or waves, of the survey. One of the features of the data set is that observations for some variables are missing for at least one wave. A model for the employment status of immigrants is developed by introducing, at the first stage of a hierarchical model, a multinomial model for the response and then subsequent terms are introduced to explain wave and subject effects. To estimate the model, we use the Gibbs sampler, which allows missing data for both the response and the explanatory variables to be imputed at each iteration of the algorithm, given some appropriate prior distributions. After accounting for significant covariate effects in the model, results show that the relative probability of remaining unemployed diminished with time following arrival in Australia.

Finite mixture regression model with random effects: application to neonatal hospital length of stay

A two-component mixture regression model that allows simultaneously for heterogeneity and dependency among observations is proposed. By specifying random effects explicitly in the linear predictor of the mixture probability and the mixture components, parameter estimation is achieved by maximising the corresponding best linear unbiased prediction type log-likelihood. Approximate residual maximum likelihood estimates are obtained via an EM algorithm in the manner of generalised linear mixed model (GLMM). The method can be extended to a g-component mixture regression model with the component density from the exponential family, leading to the development of the class of finite mixture GLMM. For illustration, the method is applied to analyse neonatal length of stay (LOS). It is shown that identification of pertinent factors that influence hospital LOS can provide important information for health care planning and resource allocation. (C) 2002 Elsevier Science B.V. All rights reserved.

Mixed model formulations for multi-environment trials

When studying genotype X environment interaction in multi-environment trials, plant breeders and geneticists often consider one of the effects, environments or genotypes, to be fixed and the other to be random. However, there are two main formulations for variance component estimation for the mixed model situation, referred to as the unconstrained-parameters (UP) and constrained-parameters (CP) formulations. These formulations give different estimates of genetic correlation and heritability as well as different tests of significance for the random effects factor. The definition of main effects and interactions and the consequences of such definitions should be clearly understood, and the selected formulation should be consistent for both fixed and random effects. A discussion of the practical outcomes of using the two formulations in the analysis of balanced data from multi-environment trials is presented. It is recommended that the CP formulation be used because of the meaning of its parameters and the corresponding variance components. When managed (fixed) environments are considered, users will have more confidence in prediction for them but will not be overconfident in prediction in the target (random) environments. Genetic gain (predicted response to selection in the target environments from the managed environments) is independent of formulation.

Methods for Categorical Longitudinal Survey Data: Understanding Employment Status of Australian Women

Many variables that are of interest in social science research are nominal variables with two or more categories, such as employment status, occupation, political preference, or self-reported health status. With longitudinal survey data it is possible to analyse the transitions of individuals between different employment states or occupations (for example). In the statistical literature, models for analysing categorical dependent variables with repeated observations belong to the family of models known as generalized linear mixed models (GLMMs). The specific GLMM for a dependent variable with three or more categories is the multinomial logit random effects model. For these models, the marginal distribution of the response does not have a closed form solution and hence numerical integration must be used to obtain maximum likelihood estimates for the model parameters. Techniques for implementing the numerical integration are available but are computationally intensive requiring a large amount of computer processing time that increases with the number of clusters (or individuals) in the data and are not always readily accessible to the practitioner in standard software. For the purposes of analysing categorical response data from a longitudinal social survey, there is clearly a need to evaluate the existing procedures for estimating multinomial logit random effects model in terms of accuracy, efficiency and computing time. The computational time will have significant implications as to the preferred approach by researchers. In this paper we evaluate statistical software procedures that utilise adaptive Gaussian quadrature and MCMC methods, with specific application to modeling employment status of women using a GLMM, over three waves of the HILDA survey.

Ventilatory changes following head-up tilt and standing in healthy subjects

Passive tilting increases ventilation in healthy subjects; however, controversy surrounds the proposed mechanism. This study is aimed to evaluate the possible mechanism for changes to ventilation following passive head-up tilt (HUT) and active standing by comparison of a range of ventilatory, metabolic and mechanical parameters. Ventilatory parameters (V (T), V (E), V (E)/VO2, V (E)/VCO2, f and PetCO(2)), functional residual capacity (FRC), respiratory mechanics with impulse oscillometry; oxygen consumption (VO2) and carbon dioxide production (VCO2) were measured in 20 healthy male subjects whilst supine, following HUT to 70 degrees and unsupported standing. Data were analysed using a linear mixed model. HUT to 70 degrees from supine increased minute ventilation (V (E)) (P < 0.001), tidal volume (V (T)) (P=0.001), ventilatory equivalent for O-2 (V (E)/VO2) (P=0.020) and the ventilatory equivalent for CO2 (V (E)/VCO2) (P < 0.001) with no change in f (P=0.488). HUT also increased FRC (P < 0.001) and respiratory system reactance (X5Hz) (P < 0.001) with reduced respiratory system resistance (R5Hz) (P=0.004) and end-tidal carbon dioxide (PetCO(2)) (P < 0.001) compared to supine. Standing increased V (E) (P < 0.001), V (T) (P < 0.001) and V (E)/VCO2 (P=0.020) with no change in respiratory rate (f) (P=0.065), V (E)/VO2 (P=0.543). Similar changes in FRC (P < 0.001), R5Hz (P=0.013), X5Hz (P < 0.001) and PetCO(2) (P < 0.001) compared to HUT were found. In contrast to HUT, standing increased VO2 (P=0.002) and VCO2 (P=0.048). The greater increase in V (E) in standing compared to HUT appears to be related to increased VO2 and VCO2 associated with increased muscle activity in the unsupported standing position. This has implications for exercise prescription and rehabilitation of critically ill patients who have reduced cardiovascular and respiratory reserve.

The rellationship between specific features of aphasia-friendly written material and comprehension of written material for people with aphasia: An exploratory study

Background: Written material is often inaccessible fro people with aphasia. The format of written material needs to be adapted to enable people with aphasia to read with understanding. Aims: This study aimed to further explore some issues raised in Rose, Worrall, and MacKenna (2003) concerning the effects of aphasia-friendly formats on the reading comprehension of people with aphasia. It was hypothesised that people with aphasia would comprehend significantly more paragraphs that were formatted in an aphasia-friendly manner than control paragraphs. This study also aimed to investigate if each single aspect of aphasia-friendly formatting (i.e., simplified vocabulary and syntax, large print, increased white spacem and pictures) used in isolation would result in increased comprehension compared to control paragraphs. Other aims were to compare the effect of aphasia-friendly fromatting with the effects of each single adaptation, and to investigate if the effects of aphasia-friendly formates were related to aphasia severity. Methods & Procedures: Participants with mild to moderately severe aphasia (N = 9) read a battery of 90 paragraphs and selected the best word of phrase from a choice of four to complete each paragraph. A linear mixed model (p < .05) was used to analyse the differences in reading comprehension with each paragraph fromat across three reading grade levels. Outcomes & Results: People with aphasia comprehended significantly more aphasia-friendly paragraphs than control paragraphs. They also comprehended significantly more paragraphs with each of the following single adaptations: simplified vocabulary and syntax, large ptint, and increased white spaces. Although people with aphasia tended to comprehend more paragraphs with pictures added than control paragraphs, this difference was not significant. No significant correlation between aphasia severity and the effect of aphasia-friendly formatting was found. Conclusion: This study supports the idea that aphasia-friendly formats increase the reading comprehension of people with aphasia. It suggests that adding pictures, particularly Clip Art pictures, may not significantly improve the reading the reading comprehension of people with aphasia. These findings have implications for all written communication with people with aphasia, both in the clinical setting and in the wider community. Applying these findings may enable people with aphasia to have equal access to written information and to participate in society.

Fitting genetic models to twin data with binary and ordered categorical responses: A comparison of structural equation modelling and Bayesian hierarchical models

We compare Bayesian methodology utilizing free-ware BUGS (Bayesian Inference Using Gibbs Sampling) with the traditional structural equation modelling approach based on another free-ware package, Mx. Dichotomous and ordinal (three category) twin data were simulated according to different additive genetic and common environment models for phenotypic variation. Practical issues are discussed in using Gibbs sampling as implemented by BUGS to fit subject-specific Bayesian generalized linear models, where the components of variation may be estimated directly. The simulation study (based on 2000 twin pairs) indicated that there is a consistent advantage in using the Bayesian method to detect a correct model under certain specifications of additive genetics and common environmental effects. For binary data, both methods had difficulty in detecting the correct model when the additive genetic effect was low (between 10 and 20%) or of moderate range (between 20 and 40%). Furthermore, neither method could adequately detect a correct model that included a modest common environmental effect (20%) even when the additive genetic effect was large (50%). Power was significantly improved with ordinal data for most scenarios, except for the case of low heritability under a true ACE model. We illustrate and compare both methods using data from 1239 twin pairs over the age of 50 years, who were registered with the Australian National Health and Medical Research Council Twin Registry (ATR) and presented symptoms associated with osteoarthritis occurring in joints of the hand.

Likelihood-based estimation of the regression model with scrambled responses

A significant problem in the collection of responses to potentially sensitive questions, such as relating to illegal, immoral or embarrassing activities, is non-sampling error due to refusal to respond or false responses. Eichhorn & Hayre (1983) suggested the use of scrambled responses to reduce this form of bias. This paper considers a linear regression model in which the dependent variable is unobserved but for which the sum or product with a scrambling random variable of known distribution, is known. The performance of two likelihood-based estimators is investigated, namely of a Bayesian estimator achieved through a Markov chain Monte Carlo (MCMC) sampling scheme, and a classical maximum-likelihood estimator. These two estimators and an estimator suggested by Singh, Joarder & King (1996) are compared. Monte Carlo results show that the Bayesian estimator outperforms the classical estimators in almost all cases, and the relative performance of the Bayesian estimator improves as the responses become more scrambled.