Statistical issues on studies of mixed longitudinal design

Mixed longitudinal designs are important study designs for many areas of medical research. Mixed longitudinal studies have several advantages over cross-sectional or pure longitudinal studies, including shorter study completion time and ability to separate time and age effects, thus are an attractive choice. Statistical methodology used in general longitudinal studies has been rapidly developing within the last few decades. Common approaches for statistical modeling in studies with mixed longitudinal designs have been the linear mixed-effects model incorporating an age or time effect. The general linear mixed-effects model is considered an appropriate choice to analyze repeated measurements data in longitudinal studies. However, common use of linear mixed-effects model on mixed longitudinal studies often incorporates age as the only random-effect but fails to take into consideration the cohort effect in conducting statistical inferences on age-related trajectories of outcome measurements. We believe special attention should be paid to cohort effects when analyzing data in mixed longitudinal designs with multiple overlapping cohorts. Thus, this has become an important statistical issue to address. ^ This research aims to address statistical issues related to mixed longitudinal studies. The proposed study examined the existing statistical analysis methods for the mixed longitudinal designs and developed an alternative analytic method to incorporate effects from multiple overlapping cohorts as well as from different aged subjects. The proposed study used simulation to evaluate the performance of the proposed analytic method by comparing it with the commonly-used model. Finally, the study applied the proposed analytic method to the data collected by an existing study Project HeartBeat!, which had been evaluated using traditional analytic techniques. Project HeartBeat! is a longitudinal study of cardiovascular disease (CVD) risk factors in childhood and adolescence using a mixed longitudinal design. The proposed model was used to evaluate four blood lipids adjusting for age, gender, race/ethnicity, and endocrine hormones. The result of this dissertation suggest the proposed analytic model could be a more flexible and reliable choice than the traditional model in terms of fitting data to provide more accurate estimates in mixed longitudinal studies. Conceptually, the proposed model described in this study has useful features, including consideration of effects from multiple overlapping cohorts, and is an attractive approach for analyzing data in mixed longitudinal design studies.^

Quantitative micrograph, HPLC and FTIR profiles of Melissa officinalis and Nepeta cataria (Lamiaceae) from Argentina

Melissa officinalis L., so called "Melissa" or "Toronjil", is a perennial aromatic herb, whose leaves are used in traditional medicine as a carminative, digestive and sedative, both in simple as in mixtures. Meanwhile, Nepeta cataria L., commonly called "Cat mint" or "Toronjil", with some similar properties, often replacing M. officinalis in the market, although their chemical composition is not completely matched, and contains an iridoid potentially toxic (nepetalactone). It is therefore necessary to establish diacritic parameters to differentiate these species, both at crude drug level, mixtures and extracts. Samples from various sources in Argentina were studied and documental specimens are preserved in the Herbarium UNSL. Anatomical sections were analyzed, and quantitative micrographic parameters were obtained, together with HPLC and FTIR spectra from methanolic and aqueous lyophilized extracts. Significant differences were detected in the prevailing smell foliage, morphology of leaves and inflorescences, trichomata type, palisade ratio, veinlet termination number, rosmarinic acid concentration (with distinctive HPLC profiles), and the CO/CH relationships obtained by FTIR from the extracts, that together allow adequate differentiation of both drugs, even when they were ground or powdered.

Secchi depth maps for the Baltic Sea, 2003-2012, with links to GeoTIFs

Secchi depth is a measure of water transparency. In the Baltic Sea region, Secchi depth maps are used to assess eutrophication and as input for habitat models. Due to their spatial and temporal coverage, satellite data would be the most suitable data source for such maps. But the Baltic Sea's optical properties are so different from the open ocean that globally calibrated standard models suffer from large errors. Regional predictive models that take the Baltic Sea's special optical properties into account are thus needed. This paper tests how accurately generalized linear models (GLMs) and generalized additive models (GAMs) with MODIS/Aqua and auxiliary data as inputs can predict Secchi depth at a regional scale. It uses cross-validation to test the prediction accuracy of hundreds of GAMs and GLMs with up to 5 input variables. A GAM with 3 input variables (chlorophyll a, remote sensing reflectance at 678 nm, and long-term mean salinity) made the most accurate predictions. Tested against field observations not used for model selection and calibration, the best model's mean absolute error (MAE) for daily predictions was 1.07 m (22%), more than 50% lower than for other publicly available Baltic Sea Secchi depth maps. The MAE for predicting monthly averages was 0.86 m (15%). Thus, the proposed model selection process was able to find a regional model with good prediction accuracy. It could be useful to find predictive models for environmental variables other than Secchi depth, using data from other satellite sensors, and for other regions where non-standard remote sensing models are needed for prediction and mapping. Annual and monthly mean Secchi depth maps for 2003-2012 come with this paper as Supplementary materials.

Model parameter

Interannual environmental variability in Peru is dominated by the El Niño Southern Oscillation (ENSO). The most dramatic changes are associated with the warm El Niño (EN) phase (opposite the cold La Niña phase), which disrupts the normal coastal upwelling and affects the dynamics of many coastal marine and terrestrial resources. This study presents a trophic model for Sechura Bay, located at the northern extension of the Peruvian upwelling system, where ENSO-induced environmental variability is most extreme. Using an initial steady-state model for the year 1996, we explore the dynamics of the ecosystem through the year 2003 (including the strong EN of 1997/98 and the weaker EN of 2002/03). Based on support from literature, we force biomass of several non-trophically-mediated 'drivers' (e.g. Scallops, Benthic detritivores, Octopus, and Littoral fish) to observe whether the fit between historical and simulated changes (by the trophic model) is improved. The results indicate that the Sechura Bay Ecosystem is a relatively inefficient system from a community energetics point of view, likely due to the periodic perturbations of ENSO. A combination of high system productivity and low trophic level target species of invertebrates (i.e. scallops) and fish (i.e. anchoveta) results in high catches and an efficient fishery. The importance of environmental drivers is suggested, given the relatively small improvements in the fit of the simulation with the addition of trophic drivers on remaining functional groups' dynamics. An additional multivariate regression model is presented for the scallop Argopecten purpuratus, which demonstrates a significant correlation between both spawning stock size and riverine discharge-mediated mortality on catch levels. These results are discussed in the context of the appropriateness of trophodynamic modeling in relatively open systems, and how management strategies may be focused given the highly environmentally influenced marine resources of the region.

Water temperature data from southern elephant seal from Marion Island with links to datasets

As the Antarctic Circumpolar Current crosses the South-West Indian Ocean Ridge, it creates an extensive eddy field characterised by high sea level anomaly variability. We investigated the diving behaviour of female southern elephant seals from Marion Island during their post-moult migrations in relation to this eddy field in order to determine its role in the animals' at-sea dispersal. Most seals dived within the region significantly more often than predicted by chance, and these dives were generally shallower and shorter than dives outside the eddy field. Mixed effects models estimated reductions of 44.33 ± 3.00 m (maximum depth) and 6.37 ± 0.10 min (dive duration) as a result of diving within the region, along with low between-seal variability (maximum depth: 5.5 % and dive duration: 8.4 %). U-shaped dives increased in frequency inside the eddy field, whereas W-shaped dives with multiple vertical movements decreased. Results suggest that Marion Island's adult female elephant seals' dives are characterised by lowered cost-of-transport when they encounter the eddy field during the start and end of their post-moult migrations. This might result from changes in buoyancy associated with varying body condition upon leaving and returning to the island. Our results do not suggest that the eddy field is a vital foraging ground for Marion Island's southern elephant seals. However, because seals preferentially travel through this area and likely forage opportunistically while minimising transport costs, we hypothesise that climate-mediated changes in the nature or position of this region may alter the seals' at-sea dispersal patterns.

Dense Map Inference with User-Defined Priors: From Priorlets to Scan Eigenvariations

When mapping is formulated in a Bayesian framework, the need of specifying a prior for the environment arises naturally. However, so far, the use of a particular structure prior has been coupled to working with a particular representation. We describe a system that supports inference with multiple priors while keeping the same dense representation. The priors are rigorously described by the user in a domain-specific language. Even though we work very close to the measurement space, we are able to represent structure constraints with the same expressivity as methods based on geometric primitives. This approach allows the intrinsic degrees of freedom of the environment’s shape to be recovered. Experiments with simulated and real data sets will be presented

LiDAR simulation in modelled orchards to optimise the use of terretrial laser scanners and derived vegetative measures

Light detection and ranging (LiDAR) technology is beginning to have an impact on agriculture. Canopy volume and/or fruit tree leaf area can be estimated using terrestrial laser sensors based on this technology. However, the use of these devices may have different options depending on the resolution and scanning mode. As a consequence, data accuracy and LiDAR derived parameters are affected by sensor configuration, and may vary according to vegetative characteristics of tree crops. Given this scenario, users and suppliers of these devices need to know how to use the sensor in each case. This paper presents a computer program to determine the best configuration, allowing simulation and evaluation of different LiDAR configurations in various tree structures (or training systems). The ultimate goal is to optimise the use of laser scanners in field operations. The software presented generates a virtual orchard, and then allows the scanning simulation with a laser sensor. Trees are created using a hidden Markov tree (HMT) model. Varying the foliar structure of the orchard the LiDAR simulation was applied to twenty different artificially created orchards with or without leaves from two positions (lateral and zenith). To validate the laser sensor configuration, leaf surface of simulated trees was compared with the parameters obtained by LiDAR measurements: the impacted leaf area, the impacted total area (leaves and wood), and th impacted area in the three outer layers of leaves.

OSIA: Out-of-order scheduling for in-order arriving in concurrent multi-path transfer.

One major problem of concurrent multi-path transfer (CMT) scheme in multi-homed mobile networks is that the utilization of different paths with diverse delays may cause packet reordering among packets of the same ?ow. In the case of TCP-like, the reordering exacerbates the problem by bringing more timeouts and unnecessary retransmissions, which eventually degrades the throughput of connections considerably. To address this issue, we ?rst propose an Out-of-order Scheduling for In-order Arriving (OSIA), which exploits the sending time discrepancy to preserve the in-order packet arrival. Then, we formulate the optimal traf?c scheduling as a constrained optimization problem and derive its closedform solution by our proposed progressive water-?lling solution. We also present an implementation to enforce the optimal scheduling scheme using cascaded leaky buckets with multiple faucets, which provides simple guidelines on maximizing the utilization of aggregate bandwidth while decreasing the probability of triggering 3 dupACKs. Compared with previous work, the proposed scheme has lower computation complexity and can also provide the possibility for dynamic network adaptability and ?ner-grain load balancing. Simulation results show that our scheme signi?cantly alleviates reordering and enhances transmission performance.

Sensorless explicit model predictive control for multi-phase buck converters with variable output voltage

The purpose of this paper is to use the predictive control to take advantage of the future information in order to improve the reference tracking. The control attempts to increase the bandwidth of the conventional regulators by using the future information of the reference, which is supposed to be known in advance. A method for designing a controller is also proposed. A comparison in simulation with a conventional regulator is made controlling a four-phase Buck converter. Advantages and disadvantages are analyzed based on simulation results.

Simulation, Design and Analysis of Air-Breathing Combined-Cycle Engines for High Speed Propulsion

Desde la aparición del turborreactor, el motor aeróbico con turbomaquinaria ha demostrado unas prestaciones excepcionales en los regímenes subsónico y supersónico bajo. No obstante, la operación a velocidades superiores requiere sistemas más complejos y pesados, lo cual ha imposibilitado la ejecución de estos conceptos. Los recientes avances tecnológicos, especialmente en materiales ligeros, han restablecido el interés por los motores de ciclo combinado. La simulación numérica de estos nuevos conceptos es esencial para estimar las prestaciones de la planta propulsiva, así como para abordar las dificultades de integración entre célula y motor durante las primeras etapas de diseño. Al mismo tiempo, la evaluación de estos extraordinarios motores requiere una metodología de análisis distinta. La tesis doctoral versa sobre el diseño y el análisis de los mencionados conceptos propulsivos mediante el modelado numérico y la simulación dinámica con herramientas de vanguardia. Las distintas arquitecturas presentadas por los ciclos combinados basados en sendos turborreactor y motor cohete, así como los diversos sistemas comprendidos en cada uno de ellos, hacen necesario establecer una referencia común para su evaluación. Es más, la tendencia actual hacia aeronaves "más eléctricas" requiere una nueva métrica para juzgar la aptitud de un proceso de generación de empuje en el que coexisten diversas formas de energía. A este respecto, la combinación del Primer y Segundo Principios define, en un marco de referencia absoluto, la calidad de la trasferencia de energía entre los diferentes sistemas. Esta idea, que se ha estado empleando desde hace mucho tiempo en el análisis de plantas de potencia terrestres, ha sido extendida para relacionar la misión de la aeronave con la ineficiencia de cada proceso involucrado en la generación de empuje. La metodología se ilustra mediante el estudio del motor de ciclo combinado variable de una aeronave para el crucero a Mach 5. El diseño de un acelerador de ciclo combinado basado en el turborreactor sirve para subrayar la importancia de la integración del motor y la célula. El diseño está limitado por la trayectoria ascensional y el espacio disponible en la aeronave de crucero supersónico. Posteriormente se calculan las prestaciones instaladas de la planta propulsiva en función de la velocidad y la altitud de vuelo y los parámetros de control del motor: relación de compresión, relación aire/combustible y área de garganta. ABSTRACT Since the advent of the turbojet, the air-breathing engine with rotating machinery has demonstrated exceptional performance in the subsonic and low supersonic regimes. However, the operation at higher speeds requires further system complexity and weight, which so far has impeded the realization of these concepts. Recent technology developments, especially in lightweight materials, have restored the interest towards combined-cycle engines. The numerical simulation of these new concepts is essential at the early design stages to compute a first estimate of the engine performance in addition to addressing airframe-engine integration issues. In parallel, a different analysis methodology is required to evaluate these unconventional engines. The doctoral thesis concerns the design and analysis of the aforementioned engine concepts by means of numerical modeling and dynamic simulation with state-of-the-art tools. A common reference is needed to evaluate the different architectures of the turbine and the rocket-based combined-cycle engines as well as the various systems within each one of them. Furthermore, the actual trend towards more electric aircraft necessitates a common metric to judge the suitability of a thrust generation process where different forms of energy coexist. In line with this, the combination of the First and the Second Laws yields the quality of the energy being transferred between the systems on an absolute reference frame. This idea, which has been since long applied to the analysis of on-ground power plants, was extended here to relate the aircraft mission with the inefficiency of every process related to the thrust generation. The methodology is illustrated with the study of a variable- combined-cycle engine for a Mach 5 cruise aircraft. The design of a turbine-based combined-cycle booster serves to highlight the importance of the engine-airframe integration. The design is constrained by the ascent trajectory and the allocated space in the supersonic cruise aircraft. The installed performance of the propulsive plant is then computed as a function of the flight speed and altitude and the engine control parameters: pressure ratio, air-to-fuel ratio and throat area.

Association of breakfast consumption with objectively measured and self-reported physical activity, sedentary time and physical fitness in European adolescents: the HELENA (Healthy Lifestyle in Europe by Nutrition in Adolescence) Study

Objective: To examine the association of breakfast consumption with objectively measured and self-reported physical activity, sedentary time and physical fitness. Design: The HELENA (Healthy Lifestyle in Europe by Nutrition in Adolescence) Cross-Sectional Study. Breakfast consumption was assessed by two non-consecutive 24 h recalls and by a ‘Food Choices and Preferences’ questionnaire. Physical activity, sedentary time and physical fitness components (cardiorespiratory fitness, muscular fitness and speed/agility) were measured and self-reported. Socio-economic status was assessed by questionnaire. Setting: Ten European cities. Subjects: Adolescents (n 2148; aged 12?5–17?5 years). Results: Breakfast consumption was not associated with measured or self-reported physical activity. However, 24 h recall breakfast consumption was related to measured sedentary time in males and females; although results were not confirmed when using other methods to assess breakfast patterns or sedentary time. Breakfast consumption was not related to muscular fitness and speed/agility in males and females. However, male breakfast consumers had higher cardiorespiratory fitness compared with occasional breakfast consumers and breakfast skippers, while no differences were observed in females. Overall, results were consistent using different methods to assess breakfast consumption or cardiorespiratory fitness (all P#0?005). In addition, both male and female breakfast skippers (assessed by 24 h recall) were less likely to have high measured cardiorespiratory fitness compared with breakfast consumers (OR50?33; 95% CI 0?18, 0?59 and OR50?56; 95 %CI 0?32, 0?98,respectively). Results persisted across methods. Conclusions: Skipping breakfast does not seem to be related to physical activity,sedentary time or muscular fitness and speed/agility as physical fitness components in European adolescents; yet it is associated with both measured and self-reported cardiorespiratory fitness, which extends previous findings.

Building a decision support system with a knowledge modeling tool

Knowledge modeling tools are software tools that follow a modeling approach to help developers in building a knowledge-based system. The purpose of this article is to show the advantages of using this type of tools in the development of complex knowledge-based decision support systems. In order to do so, the article describes the development of a system called SAIDA in the domain of hydrology with the help of the KSM modeling tool. SAIDA operates on real-time receiving data recorded by sensors (rainfall, water levels, flows, etc.). It follows a multi-agent architecture to interpret the data, predict the future behavior and recommend control actions. The system includes an advanced knowledge based architecture with multiple symbolic representation. KSM was especially useful to design and implement the complex knowledge based architecture in an efficient way.

Multi-dimensional classification with super-classes

The multi-dimensional classification problem is a generalisation of the recently-popularised task of multi-label classification, where each data instance is associated with multiple class variables. There has been relatively little research carried out specific to multi-dimensional classification and, although one of the core goals is similar (modelling dependencies among classes), there are important differences; namely a higher number of possible classifications. In this paper we present method for multi-dimensional classification, drawing from the most relevant multi-label research, and combining it with important novel developments. Using a fast method to model the conditional dependence between class variables, we form super-class partitions and use them to build multi-dimensional learners, learning each super-class as an ordinary class, and thus explicitly modelling class dependencies. Additionally, we present a mechanism to deal with the many class values inherent to super-classes, and thus make learning efficient. To investigate the effectiveness of this approach we carry out an empirical evaluation on a range of multi-dimensional datasets, under different evaluation metrics, and in comparison with high-performing existing multi-dimensional approaches from the literature. Analysis of results shows that our approach offers important performance gains over competing methods, while also exhibiting tractable running time.

Efficient Monte Carlo methods for multi-dimensional learning with classifier chains

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance – at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest-performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.

Neuronanatomy, neurology and Bayesian networks

Bayesian networks are data mining models with clear semantics and a sound theoretical foundation. In this keynote talk we will pinpoint a number of neuroscience problems that can be addressed using Bayesian networks. In neuroanatomy, we will show computer simulation models of dendritic trees and classification of neuron types, both based on morphological features. In neurology, we will present the search for genetic biomarkers in Alzheimer's disease and the prediction of health-related quality of life in Parkinson's disease. Most of these challenging problems posed by neuroscience involve new Bayesian network designs that can cope with multiple class variables, small sample sizes, or labels annotated by several experts.