Home About us Contact
|
Home About us Contact | ||
|
|
||
Marginal Models (marginal + models)
Selected AbstractsMarginal Models for Dependent, Clustered, and Longitudinal Categorical Data by BERGSMA, W., CROON, M., and HAGENAARS, J. A.BIOMETRICS, Issue 1 2010Ivy Liu No abstract is available for this article. [source] An 8-Year Prospective Study of the Relationship Between Cognitive Performance and Falling in Very Old AdultsJOURNAL OF AMERICAN GERIATRICS SOCIETY, Issue 8 2006Kaarin J. Anstey PhD OBJECTIVES: To determine whether cognitive performance, as distinct from cognitive impairment, predicts falling during an 8-year follow-up in a community-based sample of very old adults and to evaluate how cognitive change is associated with falling. DESIGN: Prospective cohort study including three waves of data collected in 1992, 1994, and 2000. SETTING: Population based, with the baseline sample drawn from the electoral roll. PARTICIPANTS: Inclusion criteria were completion of at least three cognitive tests at baseline and completion of the falls questionnaire at Wave 6 (N=539). MEASUREMENTS: Assessments of health and medical conditions, visual acuity, cognitive function, functional reach, semitandem stand, and grip strength were conducted in 1992 (baseline), 1994, and 2000. Self-report information on falls in the previous 12 months was obtained on each of these occasions. Marginal models using generalized estimating equations were used to assess the association between baseline cognitive performance and falling over 8 years, adjusting for sociodemographic, health, and sensorimotor variables. Random effects models were used to assess the relationship between change in cognitive performance and change in fall rate and fall risk over 8 years. RESULTS: Mini-Mental State Examination and verbal reasoning at baseline predicted rate of falling over an 8-year period. Within individuals, declines in verbal ability, processing speed, and immediate memory were associated with increases in rates of falling and fall risk. CONCLUSION: Cognitive performance is associated with falling over 8 years in very old adults and should be assessed in clinical practice when evaluating short- and long-term fall risk. [source] Non-fatal injuries among Pacific infants in Auckland: Data from the Pacific Islands Families First Two Years of Life studyJOURNAL OF PAEDIATRICS AND CHILD HEALTH, Issue 3 2006Philip J Schluter Aims: Child injury is the leading cause of mortality and morbidity in developed countries. While Pacific infant death rates are relatively high in New Zealand, little is known about non-fatal injury rates. We seek to describe maternally reported injury in Pacific infants aged between 0,24 months. Methods: A cohort of Pacific infants born during 2000 in Auckland, New Zealand, was followed. Maternal home interviews were conducted at 6 weeks, 12 months and 24 months postpartum and injury events were recalled. Marginal models using generalized estimating equations (GEEs) were used to analysis the longitudinal data. Results: The inception cohort included 1398 infants at 6 weeks, 1241 infants at 12 months and 1161 infants at 24 months. The age-specific injury incidence per 1000 person-years exposure was estimated at 48 (95% CI: 23, 88) injuries for infants aged 0,6 weeks, 106 (95% CI: 88, 127) injuries for infants aged 7 weeks,12 months and 174 (95% CI: 151, 199) injuries for infants aged 13,24 months. In the multivariable GEE model, older infants (P < 0.001), infants who were male (P = 0.01), born to Pacific Island fathers and non-Pacific Island mothers (P < 0.001), and in higher or unknown income groups (P = 0.01) were significantly more likely to suffer injury events. No significant two-factor interaction with infant age was identified. Conclusions: Among Pacific infants, non-fatal injury is common and injury incidence rates are considerably higher than national levels. Male infants and those born into ethnically mixed families, where the father was of Pacific Island ethnicity and the mother was non-Pacific, were at increased relative risk of injury and might benefit from specific injury prevention targeting. However, given the high injury incidence levels found, we advocate that investigation and targeting of culturally appropriate prevention strategies for all Pacific families with young children is required to reduce injury rates for Pacific infants in New Zealand. [source] Many zeros does not mean zero inflation: comparing the goodness-of-fit of parametric models to multivariate abundance dataENVIRONMETRICS, Issue 3 2005David I. Warton Abstract An important step in studying the ecology of a species is choosing a statistical model of abundance; however, there has been little general consideration of which statistical model to use. In particular, abundance data have many zeros (often 50,80 per cent of all values), and zero-inflated count distributions are often used to specifically model the high frequency of zeros in abundance data. However, in such cases it is often taken for granted that a zero-inflated model is required, and the goodness-of-fit to count distributions with and without zero inflation is not often compared for abundance data. In this article, the goodness-of-fit was compared for several marginal models of abundance in 20 multivariate datasets (a total of 1672 variables across all datasets) from different sources. Multivariate abundance data are quite commonly collected in applied ecology, and the properties of these data may differ from abundances collected in autecological studies. Goodness-of-fit was assessed using AIC values, graphs of observed vs expected proportion of zeros in a dataset, and graphs of the sample mean,variance relationship. The negative binomial model was the best fitting of the count distributions, without zero-inflation. The high frequency of zeros was well described by the systematic component of the model (i.e. at some places predicted abundance was high, while at others it was zero) and so it was rarely necessary to modify the random component of the model (i.e. fitting a zero-inflated distribution). A Gaussian model based on transformed abundances fitted data surprisingly well, and rescaled per cent cover was usually poorly fitted by a count distribution. In conclusion, results suggest that the high frequency of zeros commonly seen in multivariate abundance data is best considered to come from distributions where mean abundance is often very low (hence there are many zeros), as opposed to claiming that there are an unusually high number of zeros compared to common parametric distributions. Copyright © 2005 John Wiley & Sons, Ltd. [source] Linkage Disequilibrium Mapping of Disease Susceptibility Genes in Human PopulationsINTERNATIONAL STATISTICAL REVIEW, Issue 1 2000David Clayton Summary The paper reviews recent work on statistical methods for using linkage disequilibrium to locate disease susceptibility genes, given a set of marker genes at known positions in the genome. The paper starts by considering a simple deterministic model for linkage disequilibrium and discusses recent attempts to elaborate it to include the effects of stochastic influences, of "drift", by the use of either Writht-Fisher models or by approaches based on the coalescence of the genealogy of the sample of disease chromosomes. Most of this first part of the paper concerns a series of diallelic markers and, in this case, the models so far proposed are hierarchical probability models for multivariate binary data. Likelihoods are intractable and most approaches to linkage disequilibrium mapping amount to marginal models for pairwise associations between individual markers and the disease susceptibility locus. Approaches to evalutation of a full likelihood require Monte Carlo methods in order to integrate over the large number of unknowns. The fact that the initial state of the stochastic process which has led to present-day allele frequencies is unknown is noted and its implications for the hierarchical probability model is discussed. Difficulties and opportunities arising as a result of more polymorphic markers and extended marker haplotypes are indicated. Connections between the hierarchical modelling approach and methods based upon identity by descent and haplotype sharing by seemingly unrelated case are explored. Finally problems resulting from unknown modes of inheritance, incomplete penetrance, and "phenocopies" are briefly reviewed. Résumé Ce papier est une revue des travaux récents, protant sur les méthodes statistiques qui utilisent I'étude, des liaisons désé, quilib rées, pour identifer les génes, de susceptibilité des maladies,ápartir d'une série, de marqueurs de géncs á des positions définies du génome,. Le papier commence par considérer, un modéle, détéministe, simple pour liaisons déséquilibr,ées, puis nous discutons les améliorations, ré centes proposées, de ce modéle, dans but de tenir compte des effects des influences stochastiques soit en utilisant les modéles, de wright-fisher, soit par des approches basées, sur la coalescence de la géné alogic de I'échantillon, des chromosomes malades. La plupart de cette premiére, partie porte sur une série, de marqueurs dialléliques et, dans ce cas, les modéles, proposés, sont des modéles, hiérerchiques, probabilistes pour dinnées, binaires multivariées. Les viaisemblances n'ont pas de forme analytique et la plupart des approches pour la cartographie des liaisons déséquilibrées, sont équivalentes aux modéles, marginaux pour dinnées, appariées, entre des marqueurs individuels et le géne, de susceptibilité de la maladie.Pour évaluer, la vriausemblance compléte, des méthodes de Monte carlo sont nécessaires, afin d'intégrer, le large nombre d; inconnues. Le fait que l'état, initial du process stochastique qui a conduit éla fré, quence, allélique, actuel soit inconnu est á noter et ses implications pour le modéle, hiérarchique, probabiliste sont discutées.Les difficultés, et implications issues de marqueurs polumorphiques et de marquers haplotypes sont dévéloppées.Les liens entire l'approche de modélisation, hiérerchique, et les méthodes, d'analyse d'identite pardescendance et les haplotypes partagés, par des cas apparement non apparentés, sont explorés. Enfin les problémes, relatifs à des modes de transmission inconnus,à des pénétrances, incomplé, tes, et aux "phénocopies" sont briévenment evoqués. [source] Therapist effects in randomised controlled trials: what to do about themJOURNAL OF CLINICAL NURSING, Issue 7-8 2010Stephen J Walters Aims and objectives., The aim of this study is to describe and compare three statistical methods to allow for therapist effects in individually randomised controlled trials. Background., In an individually randomised controlled trial where the intervention is delivered by a health professional it seems likely that the effectiveness of the intervention, independent of any treatment effect, could depend on the skill of the health professional delivering it. This leads to a potential clustering of the outcomes for the patients being treated by the same health professional. Design., Retrospective statistical analysis of outcomes from four example randomised controlled trial datasets with potential clustering by health professional. Methods., Three methods to allow for clustering are described: cluster level analysis; random effects models and marginal models. These models were fitted to continuous outcome data from four example randomised controlled trial datasets with potential clustering by health professional. Results., The cluster level models produced the widest confidence intervals. Little difference was found between the estimates of the regression coefficients for the treatment effect and confidence intervals between the individual patient level models for the datasets. The conclusions reached for each dataset match those published in the original papers. The intracluster correlation coefficient ranged from <0·001,0·04 for the outcomes, which shows only minor levels of clustering within the datasets. Conclusions., The models, which use individual level data are to be preferred. Treatment coefficients from these models have different interpretations. The choice of model should depend on the scientific question being asked. Relevance to clinical practice., We recommend that researchers should be aware of any potential clustering, by health professional, in their randomised controlled trial and use appropriate methods to account for this clustering in the statistical analysis of the data. [source] Joint generalized estimating equations for multivariate longitudinal binary outcomes with missing data: an application to acquired immune deficiency syndrome dataJOURNAL OF THE ROYAL STATISTICAL SOCIETY: SERIES A (STATISTICS IN SOCIETY), Issue 1 2009Stuart R. Lipsitz Summary., In a large, prospective longitudinal study designed to monitor cardiac abnormalities in children born to women who are infected with the human immunodeficiency virus, instead of a single outcome variable, there are multiple binary outcomes (e.g. abnormal heart rate, abnormal blood pressure and abnormal heart wall thickness) considered as joint measures of heart function over time. In the presence of missing responses at some time points, longitudinal marginal models for these multiple outcomes can be estimated by using generalized estimating equations (GEEs), and consistent estimates can be obtained under the assumption of a missingness completely at random mechanism. When the missing data mechanism is missingness at random, i.e. the probability of missing a particular outcome at a time point depends on observed values of that outcome and the remaining outcomes at other time points, we propose joint estimation of the marginal models by using a single modified GEE based on an EM-type algorithm. The method proposed is motivated by the longitudinal study of cardiac abnormalities in children who were born to women infected with the human immunodeficiency virus, and analyses of these data are presented to illustrate the application of the method. Further, in an asymptotic study of bias, we show that, under a missingness at random mechanism in which missingness depends on all observed outcome variables, our joint estimation via the modified GEE produces almost unbiased estimates, provided that the correlation model has been correctly specified, whereas estimates from standard GEEs can lead to substantial bias. [source] Some alternatives in the statistical analysis of sickness absenceAMERICAN JOURNAL OF INDUSTRIAL MEDICINE, Issue 10 2009Albert Navarro Abstract Purpose Sickness absence (SA) is a commonly used outcome in occupational health cohort studies. Without the use of statistical techniques that take into account that SA is a recurrent event, the probability of obtaining biased estimates of the effects related to SA is very high. The objective of this article is to examine the application of marginal models, comparing them to count-based models, when the outcome of interest is SA. Methods By re-sampling the data of a reference study, 1,000 samples of 1,200 individuals were generated. In each of these samples, the coefficients of two factors were estimated by fitting various models: Poisson, Negative Binomial, standard Cox model for a first occurrence, Andersen,Gill and Prentice,Williams,Peterson. Results In general, differences among the models are observed in the estimates of variances and coefficients, as well as in their distribution. Specifically, the Poisson model estimates the greatest effect for both coefficients (IRR,=,1.17 and IRR,=,1.60), and the Prentice,Williams,Peterson the least effect (HR,=,1.01 and HR,=,1.26). Conclusions Whenever possible, the instantaneous form of analysis should be used for occurrences of a recurrent event. Collection of study data should be organized in order to permit recording of the most complete information possible, particularly regarding event occurrences. This should allow the presence of within-individual heterogeneity and/or occurrence dependency to be studied, and would further permit the most appropriate model to be chosen. When there is occurrence dependence, the choice of a model using the specific baseline hazard seems to be appropriate. Am. J. Ind. Med. 52:811,816, 2009. © 2009 Wiley-Liss, Inc. [source] Generalized Hierarchical Multivariate CAR Models for Areal DataBIOMETRICS, Issue 4 2005Xiaoping Jin Summary In the fields of medicine and public health, a common application of areal data models is the study of geographical patterns of disease. When we have several measurements recorded at each spatial location (for example, information on p, 2 diseases from the same population groups or regions), we need to consider multivariate areal data models in order to handle the dependence among the multivariate components as well as the spatial dependence between sites. In this article, we propose a flexible new class of generalized multivariate conditionally autoregressive (GMCAR) models for areal data, and show how it enriches the MCAR class. Our approach differs from earlier ones in that it directly specifies the joint distribution for a multivariate Markov random field (MRF) through the specification of simpler conditional and marginal models. This in turn leads to a significant reduction in the computational burden in hierarchical spatial random effect modeling, where posterior summaries are computed using Markov chain Monte Carlo (MCMC). We compare our approach with existing MCAR models in the literature via simulation, using average mean square error (AMSE) and a convenient hierarchical model selection criterion, the deviance information criterion (DIC; Spiegelhalter et al., 2002, Journal of the Royal Statistical Society, Series B64, 583,639). Finally, we offer a real-data application of our proposed GMCAR approach that models lung and esophagus cancer death rates during 1991,1998 in Minnesota counties. [source] | |||||||||||||