197,428 research outputs found
Inference in Graphical Gaussian Models with Edge and Vertex Symmetries with the gRc Package for R
Get PDFIn this paper we present the R package gRc for statistical inference in graphical Gaussian models in which symmetry restrictions have been imposed on the concentration or partial correlation matrix. The models are represented by coloured graphs where parameters associated with edges or vertices of same colour are restricted to being identical. We describe algorithms for maximum likelihood estimation and discuss model selection issues. The paper illustrates the practical use of the gRc package.
On the formation of dissolution pipes in Quaternary coastal calcareous arenites in Mediterranean settings
No full textA large number of uniform cone-shaped dissolution pipes has been observed and studied in Quaternary coastal
calcareous arenites in Apulia and Sardinia (Italy) and Tunisia. These cylindrical tubes have a mean diameter of 52·8 cm and are
up to 970 cm deep (mean depth for sediment-free pipes is 1·38 m). They generally have smooth walls along their length, are
perfectly vertical and taper out towards their bottoms. Their development is not infl uenced by bedding nor fractures. Sometimes
their walls are coated by a calcrete crust. Their morphology has been studied in detail and their relationships with the surrounding
rocks and with the environment have been analysed. The perfectly vertical development is a clear evidence of their genesis
controlled by gravity. The depth of the dissolution pipes can be described by an exponential distribution law (the Milanovic
distribution), strongly suggesting they developed by a diffusion mechanism from the surface vertically downward. We believe
dissolution pipes preferentially form in a covered karst setting. Local patches of soil and vegetation cause infi ltration water to be
enriched in carbon dioxide enhancing dissolution of carbonate cement and local small-scale subsidence. This process causes the
formation of a depression cone that guides infi ltrating waters towards these spots giving rise to the downward growth of gravitycontrolled
dissolution pipes. A change of climate from wetter phases to drier and hotter ones causes the formation of a calcrete
lining, fossilizing the pipes. When the pipes become exposed to surface agents by erosion of the sediment cover or are laterally
breached the loose quartz sand fi lling them may be transported elsewhere
Dietary arachidonic acid in perinatal nutrition: a commentary
No full textArachidonic acid (AA) is supplied together with docosahexaenoic acid (DHA) in infant formulas, but we have limited knowledge about the effects of supplementation with either of these long-chain polyunsaturated fatty acids (LCPUFA) on growth and developmental outcomes. AA is present in similar levels in breast milk throughout the world, whereas the level of DHA is highly diet dependent. Autopsy studies show similar diet-dependent variation in brain DHA, whereas AA is little affected by intake. Early intake of DHA has been shown to affect visual development, but the effect of LCPUFA on neurodevelopment remains to be established. Few studies have found any functional difference between infants supplemented with DHA alone compared to DHA+AA, but some studies show neurodevelopmental advantages in breast-fed infants of mothers supplemented with n-3 LCPUFA alone. It also remains to be established whether the AA/DHA balance could affect allergic and inflammatory outcomes later in life. Disentangling effects of genetic variability and dietary intake on AA and DHA-status and on functional outcomes may be an important step in the process of determining whether AA-intake is of any physiological or clinical importance. However, based on the current evidence we hypothesize that dietary AA plays a minor role on growth and development relative to the impact of dietary DHA
Graphical Gaussian models with symmetries
Get PDFThis thesis is concerned with graphical Gaussian models with equality constraints on the concentration or partial correlation matrix introduced by Højsgaard and Lauritzen (2008) as RCON and RCOR models. The models can be represented by vertex and edge coloured graphs G = (V,ε), where parameters associated with equally coloured vertices or edges are restricted to being identical.In the first part of this thesis we study the problem of estimability of a non-zero model mean μ if the covariance structure Σ is restricted to satisfy the constraints of an RCON or RCOR model but is otherwise unknown. Exploiting results in Kruskal (1968), we obtain a characterisation of suitable linear spaces Ω such that if Σ is restricted as above, the maximum likelihood estimator μ(with circumflex) and the least squares estimator μ* of μ coincide for μ ∈ Ω, thus allowing μ and Σ to be estimated independently. For the special case of Ω being specified by equality relations among the entries of μ according to a partition M of the model variables V, our characterisation translates into a necessary and sufficient regularity condition on M and (V,ε).In the second part we address model selection of RCON and RCOR models. Due to the large number of models, we study the structure of four model classes lying strictly within the sets of RCON and RCOR models, each of which is defined by desirable statistical properties corresponding to colouring regularity conditions. Two of these appear in Højsgaard and Lauritzen (2008), while the other two arise from the regularity condition ensuring equality of estimators μ(with circumflex) = μ* we find in the first part. We show each of the colouring classes to form complete lattices, which qualifies the corresponding model spaces for an Edwards-Havránek model selection procedure (Edwards and Havránek, 1987). We develop a coresponding algorithm for one of the model classes and give an algorithm for a systematic search in accordance with the Edwards-Havránek principles for a second class. Both are applied to data sets previously analysed in the literature, with very encouraging performances
On the origin of dissolution pipes.
No full textSeveral perfectly shaped dissolution pipes have been observed and studied in Quaternary coastal calcarenites in Sardinia and Apulia (Italy) and Tunisia. These are cylindrical tubes of 30-110 cm in diameter and up to 970 cm deep with smooth walls along their length but narrowing towards their bottoms. A model has been developed in order to understand their genesis. We believe dissolution pipes are formed by infiltrating water in a covered karst setting. Local patches of vegetation and soil would have enriched infiltrating water with carbon dioxide generating dissolution of carbonate cement and local subsidence. This process would have caused formation of a depression cone that guided infiltrating waters towards these spots giving rise to the downward growth of gravity-controlled dissolution pipes. The loose quartzite sand in these pipes would have been transported elsewhere once the pipes became exposed by erosion of the sediment cover
James M Lauritzen
No full textSeries 85298 | State Historical Society | World War I service questionnaires | James M LauritzenThis series contains military service questionnaires and photographs of Utah's World War I veterans compiled by the Utah State Historical Society shortly after the war. The forms were sent to veterans or their families to complete and return
Dr. Duane M. Jackson, Morehouse College, July 2011
No full textThis video is a conversation with Dr. Duane M. Jackson. Dr. Jackson talks about his paper, "Recall and the Serial Position Effect: The Role of Primacy and Recency on Accounting Students' Performance." Jackie Daniel, AUC Woodruff Library, is the interviewer
Combining Statistical Models
No full textThis paper develops a general framework to support the combination of information from independent but related experiments, by introducing a formal way of combining statistical models represented by families of distributions. A typical example is the combination of multivariate Gaussian families respecting conditional independence constraints, i.e. Gaussian graphical models. Combining information from such models, represented by their dependence graphs, yields a formal basis for what could suitably be termed structural meta analysis. We consider issues of combination of pairs of distributions, extending the concept of meta-Markov combination introduced by Dawid and Lauritzen. The proposed theory is then applied to the special case of graphical models
- …
