197,212 research outputs found
Jesús Villarroel, tarjeta de visita
No full textI.O. Reverso: A mi querida hermana Elvira. Jesus M. Villaroel", "Junio 3 de/75", "a los 18 años", en el sello se lee: "SCIANDRA Hos. FOTOGRAFOS", "MEXICO, Portal de Mercaderes N° 7"
José María Nava y Merelo, tarjeta de visita
No full textI.O. Anverso: "Sciandra Hermanos", "Veracruz". Reverso: "Sr. Gral. Manuel Santibañes dignese a aceptar esta debil muestra del grande aprecio con que lo distingue su verdadero y agradecido am°. José M°. Nava y Merelo. Orizaba Octe. 27/870", "10-153094.10/47"
A graphical model selection tool for mixed models
No full textModel selection can be defined as the task of estimating the performance of different models in order to choose the most parsimonious one, among a potentially very large set of candidate statistical models. We propose a graphical representation to be considered as an extension to the class of mixed models of the deviance plot proposed in the literature within the framework of classical and generalized linear models. This graphical representation allows, once a reduced number of models have been selected, to identify important covariates focusing only on the fixed effects component, assuming the random part properly specified. Nevertheless, we suggest also a standalone figure representing the residual random variance ratio: a cross-evaluation of the two graphical representations will allow to derive some conclusions on the random part specification of the model and a more accurate selection of the final model
Variable selection in mixed models: a graphical approach
No full textModel selection can be defined as the task of estimating the performance of dif-
ferent models in order to choose the (approximate) best one. The purpose of this article is to
introduce an extension of the graphical representation of deviance proposed in the framework
of classical and generalized linear models to the wider class of mixed models. The proposed
plot is useful in determining which are the important explanatory variables conditioning on
the random effects part. The applicability and the easy interpretation of the graph are illus-
trated with a real data examples
From adhesion complex to signaling hub: the dual role of dystroglycan
No full textDystroglycan (DG) is a transmembrane protein widely expressed in multiple cells and tissues. It is formed by two subunits, alpha- and beta-DG, and represents a molecular bridge between the outside and the inside of the cell, which is essential for the mechanical and structural stability of the plasma membrane. The alpha-subunit is a cell-surface protein that binds to the extracellular matrix (ECM) and is tightly associated with the plasma membrane via a non-covalent interaction with the beta-subunit, which, in turn, is a transmembrane protein that binds to the cytoskeletal actin. DG is a versatile molecule acting not only as a mechanical building block but also as a modulator of outside-inside signaling events. The cytoplasmic domain of beta-DG interacts with different adaptor and cytoskeletal proteins that function as molecular switches for the transmission of ECM signals inside the cells. These interactions can modulate the involvement of DG in different biological processes, ranging from cell growth and survival to differentiation and proliferation/regeneration. Although the molecular events that characterize signaling through the ECM-DG-cytoskeleton axis are still largely unknown, in recent years, a growing list of evidence has started to fill the gaps in our understanding of the role of DG in signal transduction. This mini-review represents an update of recent developments, uncovering the dual role of DG as an adhesion and signaling molecule that might inspire new ideas for the design of novel therapeutic strategies for pathologies such as muscular dystrophy, cardiomyopathy, and cancer, where the DG signaling hub plays important roles
Reference growth charts for assessing growth performance of Posidonia oceanica (L.) Delile
No full textPosidonia oceanica is considered a key species due to its different roles as primary producer, substrate for many species, shoreline erosion protector and long-term carbon store (1).The importance of P. oceanicahas stimulated several studies aimed at quantifying its status. In particular growth performance of rhizomes has become among the most used descriptors for monitoring changes of P. oceanicameadows induced by human or naturalexogenous factors (2). However, ability to detect any change of growth in space or in time is often confounded by natural age-induced variations, which involves serious interpretation problems (3). A general approach adopted to overcome this problem is to build growth charts as reference tool for comparison purposes. Charts describing patterns of biometric features conditioned to age are increasingly used as comparison tools, even if almost exclusively in Auxology(4). Their use can be extended to other disciplines, including ecological studies, although very large data sets are required for obtaining reliable estimates and curves should be flexible enough to account for non-linear growth pattern over age (5). In this work reference growth charts involving different P. oceanicagrowth performance measures (speed of growth and primary production of rhizomes) will be presented. Curves have been built using proper statistical frameworks (GLMM, Segmented and Quantile Regressions), based on more than 13000 annualgrowth data recorded by lepidochronology (6) on about 1600 shoots collected at 4–32 m depth range along Sicilian coasts.Growth patterns exhibited distinct trends as regards the relationships with depth: neither speed of growth nor primary production of rhizomes depended on depth until 14 m, while at deeper stands significant linear decrease by 3.5–2.0% for 1 m increase in depth was observed, due to light and sedimentation reduction. The considerable size of the dataset allowed to estimate the accurate shapes of the percentile curves (from 5thto 95th), revealing non monotonic relationships of growth with respect to shoot age with an initial increase followed by an overall decrease of 40% during the following years of the explored lifespan. The accompanying model-based classification procedures presented, will allow to obtain comparable results also when age of shoots is largely different (up to 20 years) (7). The growth charts may represent a noteworthy tool for researchers involved in studying of different aspects of seagrass monitoring. It is hoped that the proposed framework will facilitate assessment of growth performance status and comparative analysis of growth data from different populations around the Mediterranean Se
New Flexible Probability Distributions for Ranking Data
No full textRecently, several models have been proposed for analysing the ranks assigned by people to some object. These models summarize the liking feeling towards the object, possibly with respect to a set of explanatory variables. Some recent works have suggested the use of the Shifted Binomial and of the Inverse Hypergeometric distribution for modelling the approval rate, while mixture models have been considered for taking into account the uncertainty in the ranking process. We propose two new probability distributions, the Discrete Beta and the Shifted-Beta Binomial, which ensure much flexibility and allow the joint modelling of the scale (approval rate) and the shape (uncertainty) parameters of the rank distribution
A unified framework for two-dimensional clustering on preference-approvals: an analysis of Eurobarometer data
No full textQuesto articolo presenta un nuovo approccio al clustering bidimensionale
nell’ambito dei preference-approval. Il metodo proposto utilizza la tecnica
dell’unfolding per stimare le coordinate di un insieme di m individui e di un insieme
di n alternative in uno spazio p-dimensionale basato sui loro valori di prossimit`a
La principale innovazione dell’approccio `e la produzione di una rappresentazione
grafica che cattura contemporaneamente le relazioni sia tra gli individui che gli
oggetti. Viene proposta un’applicazione del metodo a dati reali, provenientei sito
Eurobarometer. La nostra analisi ha rivelato l’esistenza di due cluster di paesi con
preferenze simili, con alcuni paesi che hanno preferenze miste o uniche.This paper presents a novel approach to two-dimensional clustering within
a preference-approvals framework. The proposed method employs the ordinal unfolding
technique to estimate the coordinates of a set of m individuals and n alternatives
in a p-dimensional space based on their proximity values. The main contribution
of the approach is the production of a graphical representation that simultaneously
captures both individuals and alternatives. To explore the implications of
the proposed method, we utilize Eurobarometer data poll. Our goal is to identify
common patterns of preferences among individuals and alternatives. The analysis
reveals the existence of two main clusters of countries with similar preferences,
with some countries having mixed or unique preferences
Model interpretation from the additive elements of the PWRSS in GLMMs
No full textGeneralized Linear Mixed models(GLMMs)have rapidly become a widely used tool for modelling clustered and longitudinal data with non-Normal responses. Although a large amount of work has been done in the literature on likelihood-based inference on GLMMs,little seems to have been done on the
decomposition of the total variability associated to the different components of a mixed model.In this work we try to generalize the idea of likelihood additive elements Whittaker,1984), proposed in the context of GLMs,to the case of GLMMs by using the Penalized Weighted Residual Sum of Squares(PWRSS). The proposal is illustrated by means of areal application
- …
