Linear Mixed Models (linear + mixed_models)

Distribution by Scientific Domains

Kinds of Linear Mixed Models

  • generalized linear mixed models

  • Selected Abstracts

    Stress-induced dynamic adjustments of reproduction differentially affect fitness components of a semi-arid plant

    JOURNAL OF ECOLOGY, Issue 1 2008
    Cristina F. Aragón
    Summary 1Summer drought stress is considered the primary constraint to plant performance in Mediterranean ecosystems. However, little is known about the implications of summer stress for plant reproduction under real field conditions and, particularly, for the regulatory mechanisms of maternal investment in reproduction. 2The relationship between plant physiological status at different reproductive stages over the course of the summer drought period and final reproductive output was modelled in the Mediterranean semi-arid specialist Helianthemum squamatum. 3Plant physiological status, assessed by the chlorophyll fluorescence-based parameter Fv/Fm, and soil moisture content beneath each plant, were determined in the field at five key phenological moments in a total of 88 plants. We used Generalized Linear Mixed Models to evaluate the effect of plant physiological status at those different dates on several components of reproduction (number of flowers and seeds per plant, fruit-set and intra-fruit seed abortion). We included soil moisture as an additional predictor to statistically control its potential effect on reproduction. 4Fv/Fm measured at midday was a significant predictor of reproductive output, but its significance varied over time and with the specific reproductive response variable. Fv/Fm measured at the onset of flowering was positively related to the number of flowers and seeds per plant, whereas Fv/Fm at the fruiting peak positively affected fruit-set. Soil moisture content was only significant when measured before flowering, being positively related to total flowers and seeds. The effect of stress on reproductive output acted either at an early stage of the reproductive season, by varying the number of flowers produced and seed primordia initiated, or at a later stage, by adjusting the number or ripe fruits. 5Synthesis. Our results show a direct relationship between physiological status and reproduction, and highlight the importance of the timing of stress for reproductive success. They also show that small departures from the physiological optimum at specific reproductive stages may cause significant decreases in the reproductive output. We suggest that the dynamic adjustment of reproduction in response to stress is adaptive in fluctuating and unpredictable Mediterranean semi-arid environments, where an adequate temporal distribution of maternal resources determines the species' ability to withstand severe environmental conditions. [source]

    Linear Mixed Models: a Practical Guide using Statistical Software

    R. Allan Reese
    No abstract is available for this article. [source]

    Linear Mixed Models , A Practical Guide Using Statistical Software.


    No abstract is available for this article. [source]

    Cluster Detection Based on Spatial Associations and Iterated Residuals in Generalized Linear Mixed Models

    BIOMETRICS, Issue 2 2009
    Tonglin Zhang
    Summary Spatial clustering is commonly modeled by a Bayesian method under the framework of generalized linear mixed effect models (GLMMs). Spatial clusters are commonly detected by a frequentist method through hypothesis testing. In this article, we provide a frequentist method for assessing spatial properties of GLMMs. We propose a strategy that detects spatial clusters through parameter estimates of spatial associations, and assesses spatial aspects of model improvement through iterated residuals. Simulations and a case study show that the proposed method is able to consistently and efficiently detect the locations and magnitudes of spatial clusters. [source]

    Diagnosis of Random-Effect Model Misspecification in Generalized Linear Mixed Models for Binary Response

    BIOMETRICS, Issue 2 2009
    Xianzheng Huang
    Summary Generalized linear mixed models (GLMMs) are widely used in the analysis of clustered data. However, the validity of likelihood-based inference in such analyses can be greatly affected by the assumed model for the random effects. We propose a diagnostic method for random-effect model misspecification in GLMMs for clustered binary response. We provide a theoretical justification of the proposed method and investigate its finite sample performance via simulation. The proposed method is applied to data from a longitudinal respiratory infection study. [source]

    Bayesian Covariance Selection in Generalized Linear Mixed Models

    BIOMETRICS, Issue 2 2006
    Bo Cai
    Summary The generalized linear mixed model (GLMM), which extends the generalized linear model (GLM) to incorporate random effects characterizing heterogeneity among subjects, is widely used in analyzing correlated and longitudinal data. Although there is often interest in identifying the subset of predictors that have random effects, random effects selection can be challenging, particularly when outcome distributions are nonnormal. This article proposes a fully Bayesian approach to the problem of simultaneous selection of fixed and random effects in GLMMs. Integrating out the random effects induces a covariance structure on the multivariate outcome data, and an important problem that we also consider is that of covariance selection. Our approach relies on variable selection-type mixture priors for the components in a special Cholesky decomposition of the random effects covariance. A stochastic search MCMC algorithm is developed, which relies on Gibbs sampling, with Taylor series expansions used to approximate intractable integrals. Simulated data examples are presented for different exponential family distributions, and the approach is applied to discrete survival data from a time-to-pregnancy study. [source]

    Bayesian Prediction of Spatial Count Data Using Generalized Linear Mixed Models

    BIOMETRICS, Issue 2 2002
    Ole F. Christensen
    Summary. Spatial weed count data are modeled and predicted using a generalized linear mixed model combined with a Bayesian approach and Markov chain Monte Carlo. Informative priors for a data set with sparse sampling are elicited using a previously collected data set with extensive sampling. Furthermore, we demonstrate that so-called Langevin-Hastings updates are useful for efficient simulation of the posterior distributions, and we discuss computational issues concerning prediction. [source]

    On Estimation and Prediction for Spatial Generalized Linear Mixed Models

    BIOMETRICS, Issue 1 2002
    Hao Zhang
    Summary. We use spatial generalized linear mixed models (GLMM) to model non-Gaussian spatial variables that are observed at sampling locations in a continuous area. In many applications, prediction of random effects in a spatial GLMM is of great practical interest. We show that the minimum mean-squared error (MMSE) prediction can be done in a linear fashion in spatial GLMMs analogous to linear kriging. We develop a Monte Carlo version of the EM gradient algorithm for maximum likelihood estimation of model parameters. A by-product of this approach is that it also produces the MMSE estimates for the realized random effects at the sampled sites. This method is illustrated through a simulation study and is also applied to a real data set on plant root diseases to obtain a map of disease severity that can facilitate the practice of precision agriculture. [source]

    Dynamic Conditionally Linear Mixed Models for Longitudinal Data

    BIOMETRICS, Issue 1 2002
    M. Pourahmadi
    Summary. We develop a new class of models, dynamic conditionally linear mixed models, for longitudinal data by decomposing the within-subject covariance matrix using a special Cholesky decomposition. Here ,dynamic' means using past responses as covariates and ,conditional linearity' means that parameters entering the model linearly may be random, but nonlinear parameters are nonrandom. This setup offers several advantages and is surprisingly similar to models obtained from the first-order linearization method applied to nonlinear mixed models. First, it allows for flexible and computationally tractable models that include a wide array of covariance structures; these structures may depend on covariates and hence may differ across subjects. This class of models includes, e.g., all standard linear mixed models, antedependence models, and Vonesh-Carter models. Second, it guarantees the fitted marginal covariance matrix of the data is positive definite. We develop methods for Bayesian inference and motivate the usefulness of these models using a series of longitudinal depression studies for which the features of these new models are well suited. [source]

    Summer drought: a driver for crown condition and mortality of Norway spruce in Norway

    FOREST PATHOLOGY, Issue 2 2004
    S. Solberg
    Summary Summer drought, i.e. unusually dry and warm weather, has been a significant stress factor for Norway spruce in southeast Norway during the 14 years of forest monitoring. Dry and warm summers were followed by increases in defoliation, discolouration of foliage, cone formation and mortality. The causal mechanisms are discussed. Most likely, the defoliation resulted from increased needle-fall in the autumn after dry summers. During the monitoring period 1988,2001, southeast Norway was repeatedly affected by summer drought, in particular, in the early 1990s. The dataset comprised 455 ,Forest officers' plots' with annual data on crown condition and mortality. Linear mixed models were used for estimation and hypothesis testing, including a variance,covariance structure for the handling of random effects and temporal autocorrelation. Résumé La sécheresse estivale, c'est à dire un temps exceptionnellement sec et chaud, a été un facteur significatif de stress pour l'Epicéa commun dans le sud-est de la Norvège au cours de 14 années de surveillance. Les étés secs et chauds ont été suivis d'une augmentation de la défoliation, des colorations anormales du feuillage, de la formation de cônes et de la mortalité. Les mécanismes causaux sont discutés. La défoliation peut probablement s'expliquer par une chute automnale des aiguilles après les étés secs. Pendant la période de suivi de 1988 à 2001, le sud-est de la Norvège a été affecté de façon répétée par des sécheresses estivales, en particulier au début des années 1990. La base de données comprend 455 ,parcelles d'agents forestiers' avec des données annuelles sur l'état des houppiers et la mortalité. Des modèles linéaires mixtes ont été utilisés pour tester les hypothèses et faire les estimations, en incluant une structure de variance-covariance pour prendre en compte les effets aléatoires et les auto-corrélations temporelles. Zusammenfassung Sommertrockenheit, d.h. ungewöhnlich trockenes und warmes Wetter, war ein wesentlicher Stressfaktor für die Fichte (Picea abies) in Südwestnorwegen während der 14 Jahre, in denen der Waldzustand bisher erfasst wurde. Nach trockenen und warmen Sommern nahmen der Nadelverlust, die Nadelverfärbung, die Zapfenbildung und die Mortalität zu. Die ursächlichen Mechanismen hierfür werden diskutiert. Am wahrscheinlichsten ist der Blattverlust das Ergebnis eines erhöhten Nadelfalles im Herbst nach einem trockenen Sommer. Während der Beobachtungsperiode von 1988 bis 2001 traten in Südwestnorwegen wiederholt trockene Sommer auf, insbesondere zu Beginn der 90er Jahre. Das Datenset umfasste 455 Stichprobeflächen mit jährlichen Angaben zum Kronenzustand und zur Mortalität. Für die statistische Analyse wurden lineare Modelle mit gemischten Effekten verwendet, einschliesslich einer Varianz-Kovarianzstruktur für die zeitreihenbedingten Autokorrelationen. [source]

    The MMSE orientation for time domain is a strong predictor of subsequent cognitive decline in the elderly

    Elizabeth Guerrero-Berroa
    Abstract Background The mini-mental state exam (MMSE) has been used to address questions such as determination of appropriate cutoff scores for differentiation of individuals with intact cognitive function from patients with dementia and rate of cognitive decline. However, little is known about the relationship of performance in specific cognitive domains to subsequent overall decline. Objective To examine the specific and/or combined contribution of four MMSE domains (orientation for time, orientation for place, delayed recall, and attention) to prediction of overall cognitive decline on the MMSE. Methods Linear mixed models were applied to 505 elderly nursing home residents (mean age,=,85,,>,12 years education,=,27%; 79% F, mean follow-up,=,3.20 years) to examine the relationship between baseline scores of these domains and total MMSE scores over time. Results Orientation for time was the only domain significantly associated with MMSE decline over time. Combination of poor delayed recall with either attention or orientation for place was associated with significantly increased decline on the MMSE. Conclusions The MMSE orientation for time predicts overall decline on MMSE scores over time. A good functioning domain added to good functioning delayed recall was associated with slower rate of decline. Copyright © 2009 John Wiley & Sons, Ltd. [source]

    Maternal prenatal anxiety, postnatal caregiving and infants' cortisol responses to the still-face procedure

    Kerry-Ann Grant
    Abstract This study prospectively examined the separate and combined influences of maternal prenatal anxiety disorder and postnatal caregiving sensitivity on infants' salivary cortisol responses to the still-face procedure. Effects were assessed by measuring infant salivary cortisol upon arrival at the laboratory, and at 15-, 25-, and 40-min following the still-face procedure. Maternal symptoms of anxiety during the last 6 months of pregnancy were assessed using clinical diagnostic interview. Data analyses using linear mixed models were based on 88 women and their 7-month-old infants. Prenatal anxiety and maternal sensitivity emerged as independent, additive moderators of infant cortisol reactivity, F (3, 180),=,3.29, p,=,.02, F (3, 179),=,2.68, p,=,.05 respectively. Results were independent of maternal prenatal depression symptoms, and postnatal symptoms of anxiety and depression. Infants' stress-induced cortisol secretion patterns appear to relate not only to exposure to maternal prenatal anxiety, but also to maternal caregiving sensitivity, irrespective of prenatal psychological state. © 2009 Wiley Periodicals, Inc. Dev Psychobiol 51: 625,637, 2009 [source]

    Testing for trends in the violation frequency of an environmental threshold in rivers

    ENVIRONMETRICS, Issue 1 2009
    Lieven Clement
    Abstract Nutrient pollution in rivers is a common problem. It can provoke algae blooms which are related to increased fish mortality. To restore the water status, the regulator recently has promulgated more restrictive regulations. In Flanders for instance, the government has introduced several manure decrees (MDs) to restrict nutrient pollution. Environmental regulations are commonly expressed in terms of threshold levels. This provides a binary response to the decision maker. To handle such data, we propose the use of marginalised generalised linear mixed models. They provide valid inference on trends in the exceedance frequency. The spatio-temporal dependence of the river monitoring network is incorporated by the use of a latent variable. The temporal dependence is assumed to be AR(1) and the spatial dependence is derived from the river topology. The mean model contains a term for the trend and corrects for seasonal variation. The model formulation allows an assessment on the level of individual sampling locations and on a more regional scale. The methodology is applied to a case study on the river Yzer (Flanders). It assesses the impact of the MDs on the violation probability of the nitrate standard. A trend change is detected after the introduction of the second MD. Copyright © 2008 John Wiley & Sons, Ltd. [source]

    An echocardiographic and auscultation study of right heart responses to training in young National Hunt Thoroughbred horses

    Summary Reasons for performing study: There are few data available to determine the effect of training on cardiac valve function. Objectives: To investigate the effect of commercial race training on right ventricular (RV) and tricuspid valve function in an untrained group of National Hunt Thoroughbreds (TB). Material and methods: Cardiac auscultation, guided M-mode echocardiography of the RV, and colour flow Doppler (CFD) tricuspid valve and right atrium were performed in 90 TB horses (age 2,7 years) 1998,2003. Forty horses were examined at least once and 48 horses were examined on at least 2 occasions. Examinations were then classified as: i) before commencement of race training, ii) after cantering exercise had been sustained for a period of 8,12 weeks and iii) at full race fitness. Tricuspid valve regurgitation (TR) murmurs were graded on a 1,6 scale and CFD echocardiography TR signals were graded on a 1,9 scale. Right ventricular internal diameter (RVID) in diastole and systole (RVIDd and RVIDs) was measured by guided M-mode. Associations between continuous RVID and TR measures and explanatory covariates of weight, age, heart rate, yard and stage of training were examined using general linear mixed models with horse-level random effects. Results: On average, RVIDd and RVIDs increased by 0.08 and 0.1 cm, respectively, per year increase in age (P=0.1 and 0.02) and by 0.3 and 0.4 cm, respectively between pre-training and race fitness (P = 0.07 and 0.005). Tricuspid regurgitation score by colour flow Doppler increased by 0.6/year with age (P<0.0001) and by 1.8 between pre-training and race fitness (P< 0.0001). No significant associations were found between any outcomes and weight, heart rate and training yard. Due to the high level of co-linearity between age and training, multivariable models including both terms were not interpretable. Conclusions and clinical relevance: Athletic training of horses exerts independent effects on both severity and prevalence of tricuspid valve incompetence. This effect should therefore be taken into account when examinations are performed. Dimensions of RV increase with age and training in TB horses in a manner that appears to be similar to that of the LV. [source]

    Airway inflammation in Michigan pleasure horses: prevalence and risk factors

    N. E. Robinson
    Summary Reasons for performing study: Although subclinical airway inflammation is thought to be common in horses, there is little information on its prevalence and none on risk factors. Objective: To determine the prevalence and risk factors for an increased number of inflammatory cells and for mucus accumulation in the trachea of pleasure horses. Methods: Horses (n = 266) in stables (n = 21) in Michigan were examined endoscopically, once in winter and once in summer 2004. Visible tracheal mucoid secretions were graded 0,5 and inflammatory cell numbers counted in a tracheal lavage sample. Information collected about each horse included age, gender, presence of cough, percent time indoors and source of roughage. The repeated measures were analysed by generalised estimating equations and linear mixed models. Results: Horses eating hay, especially from round bales, had the most neutrophils, whereas horses feeding from pasture had the fewest. Being female and being outdoors in winter were associated with increased numbers of inflammatory cells. Older horses had fewer macrophages than young horses. More than 70% of horses had >20% neutrophils in tracheal lavage. Twenty percent of horses had a mucus accumulation score >1; 17% had both a mucus score >1 and >20% neutrophils. The significant risk factors for mucus accumulation >1 were age >15 years, feeding on hay as compared to pasture, and being outdoors for more than 80% time in winter. Even though mucus accumulation score >1 was a risk factor for cough, only half of such horses coughed. Cough and mucus accumulation were associated with increased number of neutrophils. Conclusions: In comparison to pasture feeding, hay feeding, particularly from round bales, was associated with an increased number of neutrophils in the airway. Being outdoors in winter was associated with increased numbers of inflammatory cells and with mucus accumulation. Because 70% of horses have >20% neutrophils, this value should not be used as the sole indicator of airway inflammation. Potential relevance: The study reinforces the importance of hay feeding and older age as risk factors for inflammatory airway disease. Horses that do not have ,heaves' may be best kept indoors when winters are cold. [source]

    Use of longitudinal data in genetic studies in the genome-wide association studies era: summary of Group 14

    Berit Kerner
    Abstract Participants analyzed actual and simulated longitudinal data from the Framingham Heart Study for various metabolic and cardiovascular traits. The genetic information incorporated into these investigations ranged from selected single-nucleotide polymorphisms to genome-wide association arrays. Genotypes were incorporated using a broad range of methodological approaches including conditional logistic regression, linear mixed models, generalized estimating equations, linear growth curve estimation, growth modeling, growth mixture modeling, population attributable risk fraction based on survival functions under the proportional hazards models, and multivariate adaptive splines for the analysis of longitudinal data. The specific scientific questions addressed by these different approaches also varied, ranging from a more precise definition of the phenotype, bias reduction in control selection, estimation of effect sizes and genotype associated risk, to direct incorporation of genetic data into longitudinal modeling approaches and the exploration of population heterogeneity with regard to longitudinal trajectories. The group reached several overall conclusions: (1) The additional information provided by longitudinal data may be useful in genetic analyses. (2) The precision of the phenotype definition as well as control selection in nested designs may be improved, especially if traits demonstrate a trend over time or have strong age-of-onset effects. (3) Analyzing genetic data stratified for high-risk subgroups defined by a unique development over time could be useful for the detection of rare mutations in common multifactorial diseases. (4) Estimation of the population impact of genomic risk variants could be more precise. The challenges and computational complexity demanded by genome-wide single-nucleotide polymorphism data were also discussed. Genet. Epidemiol. 33 (Suppl. 1):S93,S98, 2009. © 2009 Wiley-Liss, Inc. [source]

    Latitudinal patterns in the phenological responses of leaf colouring and leaf fall to climate change in Japan

    GLOBAL ECOLOGY, Issue 4 2008
    Hideyuki Doi
    ABSTRACT Aim, To estimate the potential effect of global climate change on the phenological responses of plants it is necessary to estimate spatial variations at larger scales. However, previous studies have not estimated latitudinal patterns in the phenological response directly. We hypothesized that the phenological response of plants varies with latitude, and estimated the phenological response to long-term climate change using autumn phenological events that have been delayed by recent climate change. Location, Japan. Methods, We used a 53-year data set to document the latitudinal patterns in the climate responses of the timing of autumn leaf colouring and fall for two tree species over a wide range of latitudes in Japan (31 to 44° N). We calculated single regression slopes for leaf phenological timing and air temperature across Japan and tested their latitudinal patterns using regression models. The effects of latitude, time and their interaction on the responses of the phenological timings were also estimated using generalized linear mixed models. Results, Our results showed that single regression slopes of leaf phenological timing and air temperature in autumn were positive at most stations. Higher temperatures can delay the timing of leaf phenology. Negative relationships were found between the phenological response of leaves to temperature and latitude. Single regression slopes of the phenological responses at lower latitudes were larger than those at higher latitudes. Main conclusions, We found negative relationships between leaf phenological responsiveness and latitude. These findings will be important for predicting phenological timing with global climate change. [source]

    Factors influencing territorial occupancy and reproductive output in the Booted Eagle Hieraaetus pennatus

    IBIS, Issue 4 2006
    During a 7-year research project in a forested area of southeastern Spain, we studied territorial occupancy and reproductive success in a Booted Eagle Hieraaetus pennatus population. We monitored 65 territories, gathering information on 406 occupancy events and 229 breeding attempts, including those of two potential competitors, the Northern Goshawk Accipiter gentilis and the Common Buzzard Buteo buteo. Generalized linear mixed models were used to explain occupancy and productivity, by evaluating the relative contribution of three different types of variables (habitat, competition and past events) and considering territory as a random effect. We examined a set of a priori hypothesized models, together with a number of additional models, and selected the best models following an information-theoretic approach. Our best models related territorial occupancy and productivity to previous breeding success (the fledging of one or two young), which appeared to be the most important factor determining the probability of reoccupation and the reproductive output in the subsequent year. The best occupation model revealed that the probabilities of occupancy were also conditioned by a competition variable (intraspecific nearest-neighbour distance) and two habitat variables (the location of the nest on the valley slope and the distance to the nearest forest track). Unlike the best occupation model, however, the selected model for reproductive output did not incorporate any competition variable besides previous breeding success, but included another two habitat variables (the effects of trunk height and NNE orientation). [source]

    Depressive Symptoms and Cognitive Decline in Community-Dwelling Older Adults

    Sebastian Köhler PhD
    OBJECTIVES: To examine the temporal association between depressive symptoms and cognitive functioning and estimate the effect measure modification of the apolipoprotein E (APOE) ,4 allele on this relationship. DESIGN: Prospective cohort study. SETTING: General community. PARTICIPANTS: Population-based sample of 598 cognitively intact older adults aged 60 and older, with re-assessments after 3 (N=479) and 6 years (N=412). MEASUREMENTS: Depressive symptoms (Symptom Checklist) and neurocognitive functioning (memory, Visual Verbal Learning Test; attention, Stroop Color,Word Test; processing speed, Letter Digit Substitution Test; general cognition, Mini-Mental State Examination). Longitudinal associations were assessed using linear mixed models. The risk for cognitive impairment, no dementia (CIND) was examined using logistic regression. RESULTS: Adjusting for age, sex, education, and baseline cognition, the rate of change in memory z -scores was 0.00, ,0.11, ,0.20, and ,0.37 for those in the lowest (reference group), second, third, and highest depressive symptom quartiles at baseline, respectively (P<.001 for highest vs lowest quartile). The odds ratios for developing CIND with amnestic features were 1.00, 0.87, 0.69, and 2.98 for the four severity groups (P=.05 for highest vs lowest quartile). Associations were strongest for those with persistent depressive symptoms, defined as high depressive symptoms at baseline and at least one follow-up visit. Results were similar for processing speed and global cognitive function but were not as strong for attention. No APOE interaction was observed. CONCLUSION: Depression and APOE act independently to increase the risk for cognitive decline and may provide targets for prevention and early treatment. [source]

    Relationship Between Frailty and Cognitive Decline in Older Mexican Americans

    Rafael Samper-Ternent MD
    OBJECTIVES: To examine the association between frailty status and change in cognitive function over time in older Mexican Americans. DESIGN: Data used were from the Hispanic Established Population for the Epidemiological Study of the Elderly. SETTING: Five southwestern states: Texas, New Mexico, Colorado, Arizona, and California. PARTICIPANTS: One thousand three hundred seventy noninstitutionalized Mexican-American men and women aged 65 and older with a Mini-Mental State Examination (MMSE) score of 21 or higher at baseline (1995/96). MEASUREMENTS: Frailty, defined as three or more of the following components: unintentional weight loss of more than 10 pounds, weakness (lowest 20% in grip strength), self-reported exhaustion, slow walking speed (lowest 20% in 16-foot walk time in seconds), and low physical activity level (lowest 20% on Physical Activity Scale for the Elderly score). Information about sociodemographic factors, MMSE score, medical conditions (stroke, heart attack, diabetes mellitus, arthritis, cancer, and hypertension), depressive symptoms, and visual impairment was obtained. RESULTS: Of the 1,370 subjects, 684 (49.9%) were not frail, 626 (45.7%) were prefrail (1,2 components), and 60 (4.4%) were frail (,3 components) in 1995/96. Using general linear mixed models, it was found that frail subjects had greater cognitive decline over 10 years than not frail subjects (estimate=,0.67, standard error=0.13; P<.001). This association remained statistically significant after controlling for potential confounding factors. CONCLUSION: Frail status in older Mexican Americans with MMSE scores of 21 or higher at baseline is an independent predictor of MMSE score decline over a 10-year period. Future research is needed to establish pathophysiological components that can clarify the relationship between frailty and cognitive decline. [source]

    Serum Calcium and Cognitive Function in Old Age

    Miranda T. Schram PhD
    OBJECTIVES: To determine whether serum calcium is associated with cognitive function in elderly individuals in the general population. DESIGN: Prospective follow-up study of two independent, population-based cohorts. SETTING: The Rotterdam Study (median follow-up 11 years) and the Leiden 85-plus Study (median follow-up 5 years). PARTICIPANTS: Three thousand nine hundred ninety-four individuals, mean age 71, from the Rotterdam Study and 560 individuals, all aged 85, from the Leiden 85-plus Study. MEASUREMENTS: Global cognitive function was assessed in both cohorts using the Mini-Mental State Examination; attention, psychomotor speed, and memory function were assessed in the Leiden 85-plus Study only. Linear regression and linear mixed models were used for statistical analyses. RESULTS: In the Rotterdam Study, high serum calcium was associated with worse global cognitive function at baseline (P<.05) and a faster rate of decline in cognitive function during follow-up (P=.005) in individuals aged 75 and older but not in younger individuals. In the Leiden 85-plus Study, high serum calcium was associated with worse global cognitive function from age 85 through 90 (P<.001). This observation also held for the specific cognitive domains tested (all P<.01). These results did not change when individuals with serum calcium levels greater than normal (>2.55 mmol/L) were excluded from the analyses. CONCLUSION: In the general population, high serum calcium levels are associated with faster decline in cognitive function over the age of 75. [source]

    Disentangling complex fine-scale ecological patterns by path modelling using GLMM and GIS

    Vegar Bakkestuen
    Abstract Question: How can statistical modelling tools (GLMM) and GIS be used as an aid in understanding complex ecological patterns? This general question was approached by using bryophyte demography data as an example. More specifically, we asked what is the contribution of terrain shape to explaining the performance and fate of plant individuals, controlling for all other known relationships? Location: Norway. Methods: Information on demography was obtained for 140 populations of the perennial clonal bryophyte Hylocomium splendens in Norway spruce forests during an 11-year period (1992-2002). Performance (size and branching pattern) was recorded for mature segments and fate was recorded for growing points. Positions of each of the more than 30 000 recorded bryophyte ramets were coupled with (micro-) topographic characteristics (slope and convexity) derived from fine-scale digital elevation models in a GIS framework. Carefully planned sequences of generalised linear mixed models (GLMM) were performed to test predictions from a conceptual path model. Results: We demonstrate strong dependence of size on branching, fate and on vertical position in the bryophyte carpet, and an effect of vertical position on branching pattern. Micro-topography contributed to explaining plant performance by four different mechanisms: (1) a direct effect of slope on the segment's vertical position in the carpet; (2-3) direct effects of both slope and convexity on fates of individuals via controls on risk of burial; and (4) an indirect effect of convexity on branching pattern via a direct effect on size. No indication of a direct effect of terrain on branching was found. Conclusions: Our study exemplifies the usefulness of GLMM for disentangling complex ecological relationships. Specifically, we recognise micro-topography as a potentially important factor for plant demography in general and for performance and fate of individuals in particular. [source]

    Simple means to improve the interpretability of regression coefficients

    Holger Schielzeth
    Summary 1. Linear regression models are an important statistical tool in evolutionary and ecological studies. Unfortunately, these models often yield some uninterpretable estimates and hypothesis tests, especially when models contain interactions or polynomial terms. Furthermore, the standard errors for treatment groups, although often of interest for including in a publication, are not directly available in a standard linear model. 2. Centring and standardization of input variables are simple means to improve the interpretability of regression coefficients. Further, refitting the model with a slightly modified model structure allows extracting the appropriate standard errors for treatment groups directly from the model. 3. Centring will make main effects biologically interpretable even when involved in interactions and thus avoids the potential misinterpretation of main effects. This also applies to the estimation of linear effects in the presence of polynomials. Categorical input variables can also be centred and this sometimes assists interpretation. 4. Standardization (z -transformation) of input variables results in the estimation of standardized slopes or standardized partial regression coefficients. Standardized slopes are comparable in magnitude within models as well as between studies. They have some advantages over partial correlation coefficients and are often the more interesting standardized effect size. 5. The thoughtful removal of intercepts or main effects allows extracting treatment means or treatment slopes and their appropriate standard errors directly from a linear model. This provides a simple alternative to the more complicated calculation of standard errors from contrasts and main effects. 6. The simple methods presented here put the focus on parameter estimation (point estimates as well as confidence intervals) rather than on significance thresholds. They allow fitting complex, but meaningful models that can be concisely presented and interpreted. The presented methods can also be applied to generalised linear models (GLM) and linear mixed models. [source]

    Taking the chaos out of genetic patchiness: seascape genetics reveals ecological and oceanographic drivers of genetic patterns in three temperate reef species

    MOLECULAR ECOLOGY, Issue 17 2010
    Abstract Marine species frequently show weak and/or complex genetic structuring that is commonly dismissed as ,chaotic' genetic patchiness and ecologically uninformative. Here, using three datasets that individually feature weak chaotic patchiness, we demonstrate that combining inferences across species and incorporating environmental data can greatly improve the predictive value of marine population genetics studies on small spatial scales. Significant correlations in genetic patterns of microsatellite markers among three species, kelp bass Paralabrax clathratus, Kellet's whelk Kelletia kelletii and California spiny lobster Panulirus interruptus, in the Southern California Bight suggest that slight differences in diversity and pairwise differentiation across sampling sites are not simply noise or chaotic patchiness, but are ecologically meaningful. To test whether interspecies correlations potentially result from shared environmental drivers of genetic patterns, we assembled data on kelp bed size, sea surface temperature and estimates of site-to-site migration probability derived from a high resolution multi-year ocean circulation model. These data served as predictor variables in linear models of genetic diversity and linear mixed models of genetic differentiation that were assessed with information,theoretic model selection. Kelp was the most informative predictor of genetics for all three species, but ocean circulation also played a minor role for kelp bass. The shared patterns suggest a single spatial marine management strategy may effectively protect genetic diversity of multiple species. This study demonstrates the power of environmental and ecological data to shed light on weak genetic patterns and highlights the need for future focus on a mechanistic understanding of the links between oceanography, ecology and genetic structure. [source]

    Seasonal and circadian variation in salivary testosterone in rural Bolivian men

    Virginia J. Vitzthum
    Testosterone (T) plays a key role in the increase and maintenance of muscle mass and bone density in adult men. Life history theory predicts that environmental stress may prompt a reallocation of such investments to those functions critical to survival. We tested this hypothesis in two studies of rural Bolivian adult men by comparing free T levels and circadian rhythms during late winter, which is especially severe, to those in less arduous seasons. For each pair of salivary TAM/TPM samples (collected in a , 12-h period), circadian rhythm was considered classic (CCLASSIC) if TAM > 110%TPM, reverse (CREVERSE) if TPM > 110%TAM, and flat (CFLAT) otherwise. We tested the hypotheses that mean TAM > mean TPM and that mean TLW < mean TOTHER (LW = late winter, OTHER = other seasons). In Study A, of 115 TPM,TAM pairs, 51% = CCLASSIC, 39% = CREVERSE, 10% = CFLAT; in Study B, of 184 TAM,TPM pairs, 55% = CCLASSIC, 33% = CREVERSE, 12% = CFLAT. Based on fitting linear mixed models, in both studies TOTHER-AM > TOTHER-PM (A: P = 0.035, B: P = 0.0005) and TOTHER-AM > TLW-AM (A: P = 0.054, B: P = 0.007); TPM did not vary seasonally, and T diurnality was not significant during late winter. T diurnality varied substantially between days within an individual, between individuals and between seasons, but neither T levels nor diurnality varied with age. These patterns may reflect the seasonally varying but unscheduled, life-long, strenuous physical labor that typifies many non-industrialized economies. These results also suggest that single morning samples may substantially underestimate peak circulating T for an individual and, most importantly, that exogenous signals may moderate diurnality and the trajectory of age-related change in the male gonadal axis. Am. J. Hum. Biol., 2009. © 2009 Wiley-Liss, Inc. [source]

    Follow-up of neck and shoulder pain among sewing machine operators: The Los Angeles garment study

    Pin-Chieh Wang MS
    Abstract Background The aim of the present study is to explore factors affecting or modifying self-reported neck/shoulder pain in sewing machine operators. Methods We investigated self-report neck/shoulder pain in 247 workers who participated in a 4-month prospective intervention study for musculoskeletal disorders. All participants were immigrants. We examine the influence of individual and work-related factors on changes in neck/shoulder pain during follow-up employing linear mixed models with time-spline functions. Results We observed a dramatic decline (72%) in self-reported pain intensity in the first month of follow-up, followed by a small increase from the first to fourth month (4% per month). Workers who perceived and reported their physical workload as high or worked overtime experienced less overall pain reduction. Higher baseline pain intensity, being of Hispanic ethnicity (vs. Asian), and taking cumulative daily rest time during work of 35,min or more allowing for muscles to rest were associated with a larger pain reduction in the first month, but not thereafter. Conclusion Our findings indicate that some work-related factors may be of clinical relevance for reducing neck/shoulder pain. Having lower physical workloads and less overtime work should be considered when treating patients or planning workplace interventions for managing work-related musculoskeletal disorders in this underserved immigrant population. Am. J. Ind. Med. 53:352,360, 2010. © 2009 Wiley-Liss, Inc. [source]

    On quasi-likelihood inference in generalized linear mixed models with two components of dispersion

    Brajendra C. Sutradhar
    Abstract The authors propose a quasi-likelihood approach analogous to two-way analysis of variance for the estimation of the parameters of generalized linear mixed models with two components of dispersion. They discuss both the asymptotic and small-sample behaviour of their estimators, and illustrate their use with salamander mating data. Les auteurs s'inspirent de l'analyse de la variance à deux voies pour proposer une méthode d'estimation de type quasi-vraisemblance des paramètres de modèles linéaires généralisés mixtes ayant deux composantes de dispersion. Es étudient le comportement asymptotique et à taille finie de leurs estimateurs et en illustrent l'emploi au moyen de données portant sur l'accouplement de salamandres. [source]

    Pregnancy and Birth After Kidney Donation: The Norwegian Experience

    A. V. Reisæter
    Reports on pregnancies in kidney donors are scarce. The aim was to assess pregnancy outcomes for previous donors nationwide. The Medical Birth Registry of Norway holds records of births since 1967. Linkage with the Norwegian Renal Registry provided data on pregnancies of kidney donors 1967,2002. A random sample from the Medical Birth Registry was control group, as was pregnancies in kidney donors prior to donation. Differences between groups were assessed by two-sided Fisher's exact tests and with generalized linear mixed models (GLMM). We identified 326 donors with 726 pregnancies, 106 after donation. In unadjusted analysis (Fisher) no differences were observed in the occurrence of preeclampsia (p = 0.22). In the adjusted analysis (GLMM) it was more common in pregnancies after donation, 6/106 (5.7%), than in pregnancies before donation 16/620 (2.6%) (p = 0.026). The occurrence of stillbirths after donation was 3/106 (2.8%), before donation 7/620 (1.1%), in controls (1.1%) (p = 0.17). No differences were observed in the occurrence of adverse pregnancy outcome in kidney donors and in the general population in unadjusted analysis. Our finding of more frequent preeclampsia in pregnancies after kidney donation in the secondary analysis must be interpreted with caution, as the number of events was low. [source]

    Modeling dependencies between rating categories and their effects on prediction in a credit risk portfolio

    Claudia Czado
    Abstract The internal-rating-based Basel II approach increases the need for the development of more realistic default probability models. In this paper, we follow the approach taken in McNeil A and Wendin J 7 (J. Empirical Finance 2007) by constructing generalized linear mixed models for estimating default probabilities from annual data on companies with different credit ratings. The models considered, in contrast to McNeil A and Wendin J 7 (J. Empirical Finance 2007), allow parsimonious parametric models to capture simultaneously dependencies of the default probabilities on time and credit ratings. Macro-economic variables can also be included. Estimation of all model parameters are facilitated with a Bayesian approach using Markov chain Monte Carlo methods. Special emphasis is given to the investigation of predictive capabilities of the models considered. In particular, predictable model specifications are used. The empirical study using default data from Standard and Poor's gives evidence that the correlation between credit ratings further apart decreases and is higher than the one induced by the autoregressive time dynamics. Copyright © 2008 John Wiley & Sons, Ltd. [source]

    Robust linear mixed models using the skew t distribution with application to schizophrenia data

    Hsiu J. Ho
    Abstract We consider an extension of linear mixed models by assuming a multivariate skew t distribution for the random effects and a multivariate t distribution for the error terms. The proposed model provides flexibility in capturing the effects of skewness and heavy tails simultaneously among continuous longitudinal data. We present an efficient alternating expectation-conditional maximization (AECM) algorithm for the computation of maximum likelihood estimates of parameters on the basis of two convenient hierarchical formulations. The techniques for the prediction of random effects and intermittent missing values under this model are also investigated. Our methodologies are illustrated through an application to schizophrenia data. [source]