| 1. |
- Bolin, David
(författare)
-
Models and Methods for Random Fields in Spatial Statistics with Computational Efficiency from Markov Properties
- 2012
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The focus of this work is on the development of new random field models and methods suitable for the analysis of large environmental data sets. A large part is devoted to a number of extensions to the newly proposed Stochastic Partial Differential Equation (SPDE) approach for representing Gaussian fields using Gaussian Markov Random Fields (GMRFs). The method is based on that Gaussian Matérn field can be viewed as solutions to a certain SPDE, and is useful for large spatial problems where traditional methods are too computationally intensive to use. A variation of the method using wavelet basis functions is proposed and using a simulation-based study, the wavelet approximations are compared with two of the most popular methods for efficient approximations of Gaussian fields. A new class of spatial models, including the Gaussian Matérn fields and a wide family of fields with oscillating covariance functions, is also constructed using nested SPDEs. The SPDE method is extended to this model class and it is shown that all desirable properties are preserved, such as computational efficiency, applicability to data on general smooth manifolds, and simple non-stationary extensions. Finally, the SPDE method is extended to a larger class of non-Gaussian random fields with Matérn covariance functions, including certain Laplace Moving Average (LMA) models. In particular it is shown how the SPDE formulation can be used to obtain an efficient simulation method and an accurate parameter estimation technique for a LMA model. A method for estimating spatially dependent temporal trends is also developed. The method is based on using a space-varying regression model, accounting for spatial dependency in the data, and it is used to analyze temporal trends in vegetation data from the African Sahel in order to find regions that have experienced significant changes in the vegetation cover over the studied time period. The problem of estimating such regions is investigated further in the final part of the thesis where a method for estimating excursion sets, and the related problem of finding uncertainty regions for contour curves, for latent Gaussian fields is proposed. The method is based on using a parametric family for the excursion sets in combination with Integrated Nested Laplace Approximations (INLA) and an importance sampling-based algorithm for estimating joint probabilities.
|
|
| 2. |
- Pazirandeh, Ala
(författare)
-
Purchasing Power and Purchasing Strategies - Insights From the Humanitarian Sector
- 2014
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In this dissertation, we discuss how buyers practice purchasing strategies in an asymmetric power situation favoring suppliers, and how their purchasing strategies practiced impact their purchasing power and buyer-supplier relationships. Organizations enter exchange relationships to access required resources not produced internally, and are exposed to uncertainty from not being able to fully control or predict flow of resources. Consequently they become dependent on their partners. Their level of dependence indicates the influence, or leverage they might have on the partner. Thus, firms that are highly dependent on their supplier base have less leverage or lower purchasing power. This situation can be seen in several industries; e.g. in the airline industry, in purchase of oil/gas, in monopoly supply markets, or in several purchases made by humanitarian organizations. There are several forms of purchasing strategy practiced in such situations of low purchasing power. In an exploratory pre-study of vaccine procurement in the humanitarian sector, we observed that some weaker buyers had managed to influence their supply market for better purchase terms. Considering the predictions of previous research on constraint absorption of powerful partners, this influence was surprising. In general, the focus of research has been mostly on the stronger partner in an exchange relationship, and thus less is known about the weaker partners. Thus, in this dissertation, we set to understand the purchasing strategies practiced by weaker buyers, to understand how they can have more influence on their supply than perceived. To do so, first the interrelation between purchasing power and purchasing strategies was conceptualized, based on the study of multiple buyers of vaccines for developing countries. Observations from the same multiple case study were also used to explain how purchasing strategies practiced by weaker partners can impact the buyer’s purchasing power. The predictions from this study were extended to a single case study where the impact of one specific purchasing strategy (cooperative purchasing) found from the multiple case study, was studies on the buyers’ purchasing power. This dissertation adds to previous literature, by introducing a more complete understanding of ‘‘purchasing power’’ and its elements, by increasing the understanding of purchasing strategies by less-powerful buyers and their consequence, and by increasing the understanding of purchasing strategies and operations in the humanitarian sector.
|
|
| 3. |
- Tajvidi, Nader
(författare)
-
Characterisation and Some Statistical Aspects of Univariate and Multivariate Generalised Pareto Distributions
- 1996
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Extreme value theory is about the distributions of very large or very small values in a time series or stochastic process. This has numerous applications connected with environmental science, civil engineering, materials science and insurance. A rather recent approach for modelling extreme events is the so called peak over threshold (POT) method. The generalised Pareto distribution (GPD) is a two-parameter family of distributions which can be used to model exceedances over a threshold. This thesis consists of three papers. The main focus is on some theoretical and applied statistical issues of univariate and multivariate extreme value modelling. In the first paper we compare the empirical coverage of standard bootstrap and likelihood-based confidence intervals for the parameters and 90\%-quantile of the GPD. By applying a general method of D. N. Lawley, small sample correction factors for likelihood ratio statistics of the parameters and quantiles of the GPD have been calculated. The article also investigates the performance of some bootstrap methods for estimation of accuracy measures of maximum likelihood estimators of parameters and quantiles of the GPD. In the second paper we give a multivariate analogue of the GPD and consider estimation of parameters in some specific bivariate generalised Pareto distributions (BGPD's). We generalise two of existing bivariate extreme value distributions and study maximum likelihood estimation of parameters in the corresponding BGPD's. The procedure is illustrated with an application to a bivariate series of wind data. The main interest in the thesis has been on practicality of the methods so when a new method has been developed, it's performance has been studied with the help of both real life data and simulations. In the third paper we use three previous articles as examples to illustrate difficulties which might arise in application of the theory and methods which may be used to solve them. A common theme in these articles is univariate and multivariate generalised Pareto distributions. However, the discussed problems are of a rather general nature and demonstrate some typical tasks in applied statistical research. We also discuss a general approach to design and implementation of statistical computations.
|
|
| 4. |
- Teixeira, Cristina, 1986
(författare)
-
Barley malt products for improved intestinal health
- 2016
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Barley is a good source of dietary fibre, particularly β-glucan and arabinoxylan, to increase formation of short-chain fatty acids (SCFAs). Butyric and propionic acid are involved in the preservation of colonic barrier function, thus decreasing the risk of inflammation. Previous studies have shown that malting barley increased formation of butyric acid in caecum of rats and had abundance of butyrate-producing bacteria than unmalted barley. However, this differed between malts, probably due to the differences in fibre functional characteristics.The aim of this work was to investigate the impact of barley variety and malting conditions on the functional properties of the dietary fibre in barley malt products, with the overall aim of improving intestinal health. Focus was given to β-glucan functional properties, but also arabinoxylan. The influence of these fibres on substrate delivery to the colon, SCFAs formation, microbiota composition and gene expression was investigated.In the first study, rats fed commercial barley malts had a higher level of butyric and propionic acids in the caecum and portal serum than those fed control diets (cellulose). β-glucan with broader molecular weight seemed to better increase the caecal SCFA formation. In addition, the malts contributed to improved mucosal barrier function and inflammatory state by decreasing mRNA expression of tight junction protein and toll-like receptors in the small intestine and distal colon. However, malt with high amounts of advanced glycation end-products seemed to attenuate the effect on occludin (tight junction protein) in the small intestine.To evaluate the possibility of using malting to tailor functional characteristics of the fibre, three barley varieties were malted using different temperatures and levels of lactic acid in the steeping water. The extent to which barley components changed depended on the variety. Steeping at 35°C with 0.4% lactic acid preserved soluble fibre and β-glucan content better, but not the soluble arabinoxylan, compared with steeping at 15°C and without lactic acid. However, no changes in β-glucan molecular weight (> 10 kDa) were observed. β-glucan molecular weight analysed with AF4 at a wider molecular weight range (> 2 kDa), was shown to be affected by both variety and processing (steeping or mashing) to different extents. Addition of proteolytic enzymes shifted the β-glucan of high molecular weight to a lower molecular weight range, suggesting that proteins are involved in the structure of β-glucan, which might result in an apparently higher molecular weight.After passage through a dynamic gastrointestinal in vitro model (TIM-1), it was observed that β-glucan molecular weight gradually decreased in the different barley products investigated. The longer in vitro transit time of soluble fibre and β-glucan was related to their high content and/or molecular weight, which also seemed to be linked to a higher degree of fermentation in an in vivo model (rats).In the last study it was investigated the differences of microbiota composition in rats fed barley malt products. Rats fed malt products had higher microbiota diversity (negatively associated with ulcerative colitis and obesity) than those fed barley extracts rich in arabinoxylan or β-glucan, and control. Malts contributing with a higher content of β-glucan increased the abundance of Lactobacillus and Blautia and tended to increase butyric acid, whereas soluble arabinoxylan increased Akkermansia and propionic acid in the caecum. By mixing barley products (brewers’ spent grain and malt) it was possible to modulate the microbiota into an intermediary abundance of taxa, with slight increase of butyric acid compared with malt alone.In conclusion, malting seems to be a potential processing method for tailoring barley composition to promote intestinal health. Both the selection of barley variety and the processing conditions affected the composition of malt products. The resulting barley products with a high content of soluble fibre, β-glucan and soluble arabinoxylan, enhanced colon fermentation, microbiota composition and, to some extent, the SCFA formation.
|
|
