Dietary flaxseed intake has exhibited both cardioprotective and anti-atherogenic properties. Regardless, it remains unclear whether these beneficial effects extent to the regression of atherosclerotic plaques or the resolution of cholesterol-induced vascular contractile dysfunction. In the present study, we intended to determine whether dietary flaxseed has the capacity to ameliorate vascular function abnormalities and induce atherosclerotic plaque regression. As results from previous studies using a nutritional intervention to induce atherosclerotic regression may have been confounded by premature initiation of the intervention, an appropriate feeding regimen was developed to adequately evaluate flaxseeds’ effects on atherosclerotic plaque regression. New Zealand white rabbits were utilized in two studies. To establish clear evidence of plaque growth stabilization, animals received 4 weeks of a 1% cholesterol-supplemented diet. An initial subset of animals was immediately examined. The remaining animals were fed regular rabbit chow and examined at intervals up to 28 weeks. To ascertain flaxseeds’ effects on atherosclerotic plaque regression and vascular contractile function, animals were randomly assigned to a control group fed a regular diet for 12 weeks (Group I) or an experimental group fed a 1% cholesterol-supplemented diet for 4 weeks followed by a regular diet for 8 weeks (Group II). The control and a subset of experimental animals were examined immediately afterwards. The remaining experimental animals were given an additional 8 or 14 weeks of either a regular diet (Group III and V, respectively) or a 10% flaxseed-supplemented diet (Group IV and VI, respectively) and were examined afterwards. Cholesterol feeding followed by 8 weeks of withdrawal from cholesterol not only resulted in the development and stabilization of atherosclerotic plaques but also impaired the maximum contraction caused by norepinephrine and the relaxation response to acetylcholine. An additional 14 weeks of regular diet reduced the amount of plaques on the aorta while flax-supplementation resulted in a further reduction in plaques. Nevertheless, both treatments were unable to achieve statistical significance. Flax- supplemented and regular diets improved vessel relaxation and contraction; however, negligible changes in the relaxation response induced by sodium nitroprusside were observed. Dietary flaxseed may accelerate the regression of atherosclerotic plaques. Moreover, the known beneficial effects of flaxseed do not extend to restoration of vascular function.

Climatic change has been observed in many locations and has been seen to have dramatic impact on a wide range of ecosystems. The traditional method to analyse trends in climatic series is regression analysis. Koenker and Bassett (1978) developed a regression-type model for estimating the functional relationship between predictor variables and any quantile in the distribution of the response variable. Quantile regression has received considerable attention in the statistical literature, but less so in the water resources literature. This study aims to apply quantile regression to problems in water resources and climate change studies. The core of the thesis is made up of three papers of which two have been published and one has been submitted. One paper presents a novel application of quantile regression to analyze the distribution of sea ice extent. Another paper investigates changes in temperature and precipitation extremes over the Canadian Prairies using quantile regression. The third paper presents a Bayesian model averaging method for variable selection adapted to quantile regression and analyzes the relationship of extreme precipitation with large-scale atmospheric variables. This last paper also develops a novel statistical downscaling model based on quantile regression. The various applications of quantile regression support the conclusion that the method is useful in climate change studies.

No description available.

No description available.

No description available.

Semiparametric regression is playing an increasingly large role in the analysis of datasets exhibiting various complications (Ruppert, Wand & Carroll, 2003). In particular semiparametric regression a plays prominent role in the area of data mining where such complications are numerous (Hastie, Tibshirani & Friedman, 2001). In this thesis we develop fast, interpretable methods addressing many of the difficulties associated with data mining applications including: model selection, missing value analysis, outliers and heteroscedastic noise. We focus on function estimation using penalised splines via mixed model methodology (Wahba 1990; Speed 1991; Ruppert et al. 2003). In dealing with the difficulties associated with data mining applications many of the models we consider deviate from typical normality assumptions. These models lead to likelihoods involving analytically intractable integrals. Thus, in keeping with the aim of speed, we seek analytic approximations to such integrals which are typically faster than numeric alternatives. These analytic approximations not only include popular penalised quasi-likelihood (PQL) approximations (Breslow & Clayton, 1993) but variational approximations. Originating in physics, variational approximations are a relatively new class of approximations (to statistics) which are simple, fast, flexible and effective. They have recently been applied to statistical problems in machine learning where they are rapidly gaining popularity (Jordan, Ghahramani, Jaakkola & Sau11999; Corduneanu & Bishop, 2001; Ueda & Ghahramani, 2002; Bishop & Winn, 2003; Winn & Bishop 2005). We develop variational approximations to: generalized linear mixed models (GLMMs); Bayesian GLMMs; simple missing values models; and for outlier and heteroscedastic noise models, which are, to the best of our knowledge, new. These methods are quite effective and extremely fast, with fitting taking minutes if not seconds on a typical 2008 computer. We also make a contribution to variational methods themselves. Variational approximations often underestimate the variance of posterior densities in Bayesian models (Humphreys & Titterington, 2000; Consonni & Marin, 2004; Wang & Titterington, 2005). We develop grid-based variational posterior approximations. These approximations combine a sequence of variational posterior approximations, can be extremely accurate and are reasonably fast.

Semiparametric regression is playing an increasingly large role in the analysis of datasets exhibiting various complications (Ruppert, Wand & Carroll, 2003). In particular semiparametric regression a plays prominent role in the area of data mining where such complications are numerous (Hastie, Tibshirani & Friedman, 2001). In this thesis we develop fast, interpretable methods addressing many of the difficulties associated with data mining applications including: model selection, missing value analysis, outliers and heteroscedastic noise. We focus on function estimation using penalised splines via mixed model methodology (Wahba 1990; Speed 1991; Ruppert et al. 2003). In dealing with the difficulties associated with data mining applications many of the models we consider deviate from typical normality assumptions. These models lead to likelihoods involving analytically intractable integrals. Thus, in keeping with the aim of speed, we seek analytic approximations to such integrals which are typically faster than numeric alternatives. These analytic approximations not only include popular penalised quasi-likelihood (PQL) approximations (Breslow & Clayton, 1993) but variational approximations. Originating in physics, variational approximations are a relatively new class of approximations (to statistics) which are simple, fast, flexible and effective. They have recently been applied to statistical problems in machine learning where they are rapidly gaining popularity (Jordan, Ghahramani, Jaakkola & Sau11999; Corduneanu & Bishop, 2001; Ueda & Ghahramani, 2002; Bishop & Winn, 2003; Winn & Bishop 2005). We develop variational approximations to: generalized linear mixed models (GLMMs); Bayesian GLMMs; simple missing values models; and for outlier and heteroscedastic noise models, which are, to the best of our knowledge, new. These methods are quite effective and extremely fast, with fitting taking minutes if not seconds on a typical 2008 computer. We also make a contribution to variational methods themselves. Variational approximations often underestimate the variance of posterior densities in Bayesian models (Humphreys & Titterington, 2000; Consonni & Marin, 2004; Wang & Titterington, 2005). We develop grid-based variational posterior approximations. These approximations combine a sequence of variational posterior approximations, can be extremely accurate and are reasonably fast.

Semiparametric regression is playing an increasingly large role in the analysis of datasets exhibiting various complications (Ruppert, Wand & Carroll, 2003). In particular semiparametric regression a plays prominent role in the area of data mining where such complications are numerous (Hastie, Tibshirani & Friedman, 2001). In this thesis we develop fast, interpretable methods addressing many of the difficulties associated with data mining applications including: model selection, missing value analysis, outliers and heteroscedastic noise. We focus on function estimation using penalised splines via mixed model methodology (Wahba 1990; Speed 1991; Ruppert et al. 2003). In dealing with the difficulties associated with data mining applications many of the models we consider deviate from typical normality assumptions. These models lead to likelihoods involving analytically intractable integrals. Thus, in keeping with the aim of speed, we seek analytic approximations to such integrals which are typically faster than numeric alternatives. These analytic approximations not only include popular penalised quasi-likelihood (PQL) approximations (Breslow & Clayton, 1993) but variational approximations. Originating in physics, variational approximations are a relatively new class of approximations (to statistics) which are simple, fast, flexible and effective. They have recently been applied to statistical problems in machine learning where they are rapidly gaining popularity (Jordan, Ghahramani, Jaakkola & Sau11999; Corduneanu & Bishop, 2001; Ueda & Ghahramani, 2002; Bishop & Winn, 2003; Winn & Bishop 2005). We develop variational approximations to: generalized linear mixed models (GLMMs); Bayesian GLMMs; simple missing values models; and for outlier and heteroscedastic noise models, which are, to the best of our knowledge, new. These methods are quite effective and extremely fast, with fitting taking minutes if not seconds on a typical 2008 computer. We also make a contribution to variational methods themselves. Variational approximations often underestimate the variance of posterior densities in Bayesian models (Humphreys & Titterington, 2000; Consonni & Marin, 2004; Wang & Titterington, 2005). We develop grid-based variational posterior approximations. These approximations combine a sequence of variational posterior approximations, can be extremely accurate and are reasonably fast.

Thesis ( Ph.D.) -- McMaster University, 2002. / Includes bibliographical references. Also available via World Wide Web.

Zugl.: München, Univ., Diss., 2007