Home About us Contact
|
Home About us Contact | ||
|
|
||
Mixed-effects Models (mixed-effect + models)
Selected AbstractsQuantitative imaging of cartilage morphology at 3.0 Tesla in the presence of gadopentate dimeglumine (Gd-DTPA)MAGNETIC RESONANCE IN MEDICINE, Issue 2 2007Felix Eckstein Abstract MRI-based cartilage morphometry was previously validated in the absence of gadopentate dimeglumine (Gd-DTPA). However, Gd-DTPA is required for compositional (proteoglycan) imaging using delayed gadolinium-enhanced MRI of cartilage (dGEMRIC). Therefore, the effect of Gd-DTPA on cartilage morphometry was studied. A total of 165 female participants (67 with and 98 without osteoarthritis [OA]) were imaged at 3.0 Tesla before and 2 hr after intravenous Gd-DTPA injection. Flip angles in post-Gd-DTPA scans varied between 12° and 35°. Cartilage volume and thickness of post- vs. pre-Gd-DTPA scans showed intraclass correlation coefficients (ICCs) of 0.85 , r , 0.95, mean differences between ,2.1% and +1.1%, and standard deviations (SDs) of differences between 4.7% and 9.2%. Mixed-effect models found no consistent impact of flip angle and OA status on post- vs. pre-Gd-DTPA differences. Accurate morphological measurements of cartilage can be obtained after Gd-DTPA injection, allowing compositional and morphological imaging to be combined into one session. Magn Reson Med 58:402,406, 2007. © 2007 Wiley-Liss, Inc. [source] Plasticity in vertical behaviour of migrating juvenile southern bluefin tuna (Thunnus maccoyii) in relation to oceanography of the south Indian OceanFISHERIES OCEANOGRAPHY, Issue 4 2009SOPHIE BESTLEY Abstract Electronic tagging provides unprecedented information on the habitat use and behaviour of highly migratory marine predators, but few analyses have developed quantitative links between animal behaviour and their oceanographic context. In this paper we use archival tag data from juvenile southern bluefin tuna (Thunnus maccoyii, SBT) to (i) develop a novel approach characterising the oceanographic habitats used throughout an annual migration cycle on the basis of water column structure (i.e., temperature-at-depth data from tags), and (ii) model how the vertical behaviour of SBT altered in relation to habitat type and other factors. Using this approach, we identified eight habitat types occupied by juvenile SBT between the southern margin of the subtropical gyre and the northern edge of the Subantarctic Front in the south Indian Ocean. Although a high degree of variability was evident both within and between fish, mixed-effect models identified consistent behavioural responses to habitat, lunar phase, migration status and diel period. Our results indicate SBT do not act to maintain preferred depth or temperature ranges, but rather show highly plastic behaviours in response to changes in their environment. This plasticity is discussed in terms of the potential proximate causes (physiological, ecological) and with reference to the challenges posed for habitat-based standardisation of fishery data used in stock assessments. [source] Variability explained by covariates in linear mixed-effect models for longitudinal dataTHE CANADIAN JOURNAL OF STATISTICS, Issue 3 2010Bo Hu Abstract Variability explained by covariates or explained variance is a well-known concept in assessing the importance of covariates for dependent outcomes. In this paper we study R2 statistics of explained variance pertinent to longitudinal data under linear mixed-effect models, where the R2 statistics are computed at two different levels to measure, respectively, within- and between-subject variabilities explained by the covariates. By deriving the limits of R2 statistics, we find that the interpretation of explained variance for the existing R2 statistics is clear only in the case where the covariance matrix of the outcome vector is compound symmetric. Two new R2 statistics are proposed to address the effect of time-dependent covariate means. In the general case where the outcome covariance matrix is not compound symmetric, we introduce the concept of compound symmetry projection and use it to define level-one and level-two R2 statistics. Numerical results are provided to support the theoretical findings and demonstrate the performance of the R2 statistics. The Canadian Journal of Statistics 38: 352,368; 2010 © 2010 Statistical Society of Canada La variation expliquée par les covariables (ou la variance expliquée) est un concept bien connu pour mesurer l'importance de ces covariables sur la variable dépendante. Dans cet article, nous étudions la statistique du R carré pour la variance expliquée pertinente aux données longitudinales pour des modèles linéaires à effets mixtes. La statistique du R carré est calculée à deux niveaux différents pour mesurer la variation expliquée par les covariables à l'intérieur et entre les sujets. En obtenant des limites aux statistiques du R carré, nous trouvons que l'interprétation de la variance expliquée pour les statistiques du R carré existantes est claire seulement dans le cas où la matrice de variance-covariance des observations dépendantes est symétrique composée. Deux nouvelles statistiques du R carré sont proposées afin de prendre en compte les effets des moyennes des covariables pouvant dépendre du temps. Dans le cas général où la matrice de variance-covariance des observations n'est pas symétrique composée, nous introduisons le concept de projection symétrique composée et nous l'utilisons pour définir les statistiques du R carré de niveaux 1 et 2. Des résultats numériques appuient nos résultats théoriques et ils montrent la performance des statistiques du R carré. La revue canadienne de statistique 38: 352,368; 2010 © 2010 Société statistique du Canada [source] Neutrophil gelatinase,associated lipocalin is a predictor of the course of global and renal childhood-onset systemic lupus erythematosus disease activityARTHRITIS & RHEUMATISM, Issue 9 2009Claas H. Hinze Objective To determine whether neutrophil gelatinase,associated lipocalin (NGAL) can predict worsening of global and renal disease activity in childhood-onset systemic lupus erythematosus (SLE). Methods One hundred eleven patients with childhood-onset SLE were enrolled in a longitudinal, prospective study with quarterly study visits and had at least 3 study visits. At each visit, global disease activity was measured using 3 external standards: the numerically converted British Isles Lupus Assessment Group (BILAG) index, the SLE Disease Activity Index 2000 update score, and the physician's assessment of global disease activity. Renal and extrarenal disease activity were measured by the respective domain scores. The disease course over time was categorized at the most recent visit (persistently active, persistently inactive, improved, or worsening). Plasma and urinary NGAL levels were measured by enzyme-linked immunosorbent assay, and urinary NGAL levels were standardized to the urinary creatinine concentration. The longitudinal changes in NGAL levels were compared with the changes in SLE disease activity using mixed-effect models. Results Significant increases in standardized urinary NGAL levels of up to 104% were detected up to 3 months before worsening of lupus nephritis (as measured by all 3 external standards). Plasma NGAL levels increased significantly by as much as 26% up to 3 months before worsening of global SLE disease activity as measured by all 3 external standards. Plasma NGAL levels increased significantly by 26% as early as 3 months prior to worsening of lupus nephritis as measured by the BILAG renal score. Conclusion Serial measurement of urinary and plasma NGAL levels may be valuable in predicting impending worsening of global and renal childhood-onset SLE disease activity. [source] Heart rate variability in response to pain stimulus in VLBW infants followed longitudinally during NICU stayDEVELOPMENTAL PSYCHOBIOLOGY, Issue 8 2009Nikhil S. Padhye Abstract The objective of this longitudinal study, conducted in a neonatal intensive care unit, was to characterize the response to pain of high-risk very low birth weight infants (<1,500,g) from 23 to 38 weeks post-menstrual age (PMA) by measuring heart rate variability (HRV). Heart period data were recorded before, during, and after a heel lanced or wrist venipunctured blood draw for routine clinical evaluation. Pain response to the blood draw procedure and age-related changes of HRV in low-frequency and high-frequency bands were modeled with linear mixed-effects models. HRV in both bands decreased during pain, followed by a recovery to near-baseline levels. Venipuncture and mechanical ventilation were factors that attenuated the HRV response to pain. HRV at the baseline increased with post-menstrual age but the growth rate of high-frequency power was reduced in mechanically ventilated infants. There was some evidence that low-frequency HRV response to pain improved with advancing PMA. © 2009 Wiley Periodicals, Inc. Dev Psychobiol 51: 638,649, 2009 [source] Prediction of lethal/effective concentration/dose in the presence of multiple auxiliary covariates and components of varianceENVIRONMENTAL TOXICOLOGY & CHEMISTRY, Issue 9 2007Steve Gutreuter Abstract Predictors of the percentile lethal/effective concentration/dose are commonly used measures of efficacy and toxicity. Typically such quantal-response predictors (e.g., the exposure required to kill 50% of some population) are estimated from simple bioassays wherein organisms are exposed to a gradient of several concentrations of a single agent. The toxicity of an agent may be influenced by auxiliary covariates, however, and more complicated experimental designs may introduce multiple variance components. Prediction methods lag examples of those cases. A conventional two-stage approach consists of multiple bivariate predictions of, say, medial lethal concentration followed by regression of those predictions on the auxiliary covariates. We propose a more effective and parsimonious class of generalized nonlinear mixed-effects models for prediction of lethal/effective dose/concentration from auxiliary covariates. We demonstrate examples using data from a study regarding the effects of pH and additions of variable quantities 2',5'-dichloro-4'-nitrosalicylanilide (niclosamide) on the toxicity of 3-trifluoromethyl-4-nitrophenol to larval sea lamprey (Petromyzon marinus). The new models yielded unbiased predictions and root-mean-squared errors (RMSEs) of prediction for the exposure required to kill 50 and 99.9% of some population that were 29 to 82% smaller, respectively, than those from the conventional two-stage procedure. The model class is flexible and easily implemented using commonly available software. [source] Intraseasonal climate and habitat-specific variability controls the flowering phenology of high alpine plant speciesFUNCTIONAL ECOLOGY, Issue 2 2010Karl Hülber Summary 1. ,High alpine plants endure a cold climate with short growing seasons entailing severe consequences of an improper timing of development. Hence, their flowering phenology is expected to be rigorously controlled by climatic factors. 2. ,We studied ten alpine plant species from habitats with early and late melting snow cover for 2 years and compared the synchronizing effect of temperature sums (TS), time of snowmelt (SM) and photoperiod (PH) on their flowering phenology. Intraseasonal and habitat-specific variation in the impact of these factors was analysed by comparing predictions of time-to-event models using linear mixed-effects models. 3. ,Temperature was the overwhelming trigger of flowering phenology for all species. Its synchronizing effect was strongest at or shortly after flowering indicating the particular importance of phenological control of pollination. To some extent, this pattern masks the common trend of decreasing phenological responses to climatic changes from the beginning to the end of the growing season for lowland species. No carry-over effects were detected. 4. ,As expected, the impact of photoperiod was weaker for snowbed species than for species inhabiting sites with early melting snow cover, while for temperature the reverse pattern was observed. 5. ,Our findings provide strong evidence that alpine plants will respond quickly and directly to increasing temperature without considerable compensation due to photoperiodic control of phenology. [source] Global evidence that deforestation amplifies flood risk and severity in the developing worldGLOBAL CHANGE BIOLOGY, Issue 11 2007COREY J. A. BRADSHAW Abstract With the wide acceptance of forest-protection policies in the developing world comes a requirement for clear demonstrations of how deforestation may erode human well-being and economies. For centuries, it has been believed that forests provide protection against flooding. However, such claims have given rise to a heated polemic, and broad-scale quantitative evidence of the possible role of forests in flood protection has not been forthcoming. Using data collected from 1990 to 2000 from 56 developing countries, we show using generalized linear and mixed-effects models contrasted with information-theoretic measures of parsimony that flood frequency is negatively correlated with the amount of remaining natural forest and positively correlated with natural forest area loss (after controlling for rainfall, slope and degraded landscape area). The most parsimonious models accounted for over 65% of the variation in flood frequency, of which nearly 14% was due to forest cover variables alone. During the decade investigated, nearly 100 000 people were killed and 320 million people were displaced by floods, with total reported economic damages exceeding US$1151 billion. Extracted measures of flood severity (flood duration, people killed and displaced, and total damage) showed some weaker, albeit detectable correlations to natural forest cover and loss. Based on an arbitrary decrease in natural forest area of 10%, the model-averaged prediction of flood frequency increased between 4% and 28% among the countries modeled. Using the same hypothetical decline in natural forest area resulted in a 4,8% increase in total flood duration. These correlations suggest that global-scale patterns in mean forest trends across countries are meaningful with respect to flood dynamics. Unabated loss of forests may increase or exacerbate the number of flood-related disasters, negatively impact millions of poor people, and inflict trillions of dollars in damage in disadvantaged economies over the coming decades. This first global-scale empirical demonstration that forests are correlated with flood risk and severity in developing countries reinforces the imperative for large-scale forest protection to protect human welfare, and suggests that reforestation may help to reduce the frequency and severity of flood-related catastrophes. [source] Genome-wide pleiotropy of osteoporosis-related phenotypes: The framingham studyJOURNAL OF BONE AND MINERAL RESEARCH, Issue 7 2010David Karasik Abstract Genome-wide association studies offer an unbiased approach to identify new candidate genes for osteoporosis. We examined the Affymetrix 500K,+,50K SNP GeneChip marker sets for associations with multiple osteoporosis-related traits at various skeletal sites, including bone mineral density (BMD, hip and spine), heel ultrasound, and hip geometric indices in the Framingham Osteoporosis Study. We evaluated 433,510 single-nucleotide polymorphisms (SNPs) in 2073 women (mean age 65 years), members of two-generational families. Variance components analysis was performed to estimate phenotypic, genetic, and environmental correlations (,P, ,G, and ,E) among bone traits. Linear mixed-effects models were used to test associations between SNPs and multivariable-adjusted trait values. We evaluated the proportion of SNPs associated with pairs of the traits at a nominal significance threshold ,,=,0.01. We found substantial correlation between the proportion of associated SNPs and the ,P and ,G (r,=,0.91 and 0.84, respectively) but much lower with ,E (r,=,0.38). Thus, for example, hip and spine BMD had 6.8% associated SNPs in common, corresponding to ,P,=,0.55 and ,G,=,0.66 between them. Fewer SNPs were associated with both BMD and any of the hip geometric traits (eg, femoral neck and shaft width, section moduli, neck shaft angle, and neck length); ,G between BMD and geometric traits ranged from ,0.24 to +0.40. In conclusion, we examined relationships between osteoporosis-related traits based on genome-wide associations. Most of the similarity between the quantitative bone phenotypes may be attributed to pleiotropic effects of genes. This knowledge may prove helpful in defining the best phenotypes to be used in genetic studies of osteoporosis. © 2010 American Society for Bone and Mineral Research [source] Mixed-effects models in psychophysiologyPSYCHOPHYSIOLOGY, Issue 1 2000Emilia Bagiella The current methodological policy in Psychophysiology stipulates that repeated-measures designs be analyzed using either multivariate analysis of variance (ANOVA) or repeated-measures ANOVA with the Greenhouse,Geisser or Huynh,Feldt correction. Both techniques lead to appropriate type I error probabilities under general assumptions about the variance-covariance matrix of the data. This report introduces mixed-effects models as an alternative procedure for the analysis of repeated-measures data in Psychophysiology. Mixed-effects models have many advantages over the traditional methods: They handle missing data more effectively and are more efficient, parsimonious, and flexible. We described mixed-effects modeling and illustrated its applicability with a simple example. [source] Polymorphism of the ovine ,3 -adrenergic receptor gene (ADRB3) and its association with wool mean staple strength and yieldANIMAL GENETICS, Issue 6 2009R. H. Forrest Summary We investigated the possibility that variation in ovine ADRB3 is associated with various wool traits, in particular mean staple strength (MSS). Polymerase chain reaction-single strand conformational polymorphism analysis of part of the ADRB3 intron was used to genotype 695 Merino lambs born on three farms in the South Island of New Zealand and which were shorn as 2-tooths. For each fleece, MSS, mean fibre diameter, mean staple length and yield were measured. The results from mixed-effects models and half-sib analyses suggest that ADRB3 alleles A and D have a negative impact on some wool traits, whereas ADRB3 alleles C and E appear to have a positive impact, with allele C potentially having a greater impact than allele E on MSS. This variation in the ADRB3 may assist in the genetic selection for increased MSS and yield in Merino sheep. [source] Discriminant Analysis for Longitudinal Data with Multiple Continuous Responses and Possibly Missing DataBIOMETRICS, Issue 1 2009Guillermo Marshall Summary Multiple outcomes are often used to properly characterize an effect of interest. This article discusses model-based statistical methods for the classification of units into one of two or more groups where, for each unit, repeated measurements over time are obtained on each outcome. We relate the observed outcomes using multivariate nonlinear mixed-effects models to describe evolutions in different groups. Due to its flexibility, the random-effects approach for the joint modeling of multiple outcomes can be used to estimate population parameters for a discriminant model that classifies units into distinct predefined groups or populations. Parameter estimation is done via the expectation-maximization algorithm with a linear approximation step. We conduct a simulation study that sheds light on the effect that the linear approximation has on classification results. We present an example using data from a study in 161 pregnant women in Santiago, Chile, where the main interest is to predict normal versus abnormal pregnancy outcomes. [source] | ||||||||||||||||