The current study proposed a new model, termed the cross-classified multiple membership latent variable regression (CCMM-LVR) model, to be utilized for multiple membership data structures (for example, in the presence of student mobility across schools) that provides an extension to the three-level latent variable regression model (HM3-LVR). The HM3-LVR model is beneficial for testing more flexible, directional hypotheses about growth trajectory parameters and handles pure clustering of participants within higher-level units. However, the HM3-LVR model involves the assumption that students remain in the same cluster (school) throughout the duration of the time period of interest. The CCMM-LVR model, on the other hand, appropriately models the participants’ changing clusters over time. The first purpose of this study was to demonstrate use and interpretation of the CCMM-LVR model and its parameters with a large-scale longitudinal dataset that had a multiple membership data structure (i.e., student mobility). The impact of ignoring mobility in the real data was investigated by comparing parameter estimates, standard error estimates, and model fit indices for the two estimating models (CCMM-LVR and HM3-LVR). The second purpose of the dissertation was to conduct a simulation study to try to understand the source of potential differences between the two estimating models and find out which model’s estimates were closer to the truth given the conditions investigated. The manipulated conditions in the simulation study included the mobility rate, number of clustering units, number of individuals (i.e., students) per cluster (here, school), and number of measurement occasions per individual. The outcomes investigated in the simulation study included relative parameter bias, relative standard error bias, root mean square error, and coverage rates of the 95% credible intervals. Substantial bias was found across conditions for both models, but the CCMM-LVR model resulted in the least amount of relative parameter bias and more efficient estimates of the parameters, especially for larger numbers of clustering units. The results of the real data and simulation studies are discussed, along with the implications for applied researchers for when to consider using the CCMM-LVR model versus the misspecified HM3-LVR model. / text

Many health technologies exhibit some form of learning effect, and this represents a barrier to rigorous assessment by randomised controlled trials. There is reluctance to evaluate while the technique is being learnt, yet unwillingness to admit uncertainty once it has been learnt. In principle, statistical description of a learning curve and subsequent adjustment of an evaluation to take account of learning effects should solve this problem. Exactly how the analyses should be performed has been unclear. This thesis has three components: Systematic review of health technology assessment literature: a systematic description of studies that directly assessed the learning curve effect of health technologies. Systematic search of non-health technology assessment literature: a systematic identification of 'novel' statistical techniques applied to learning curve data in other fields, such as psychology and manufacturing. Testing of statistical methods: testing of these statistical techniques in sets of data describing a variety of health technologies where learning curve effects are known to exist.

Master of Arts / Department of Economics / Lloyd B. Thomas / A negative-sloped Treasury curve is often cited in financial news articles and by Federal Reserve economists as a predictor of recessions. This report reviews previously published research examining the reliability of yield curves predicting recessions. Findings show that the yield curve inverts two or more quarters before recessions, with short-term interest rates rising above long-term interest rates. Probit regression has proven a reliable method for generating estimated probabilities of future recessions that, in turn, are useful for both monetary policy and asset allocation decision-making.

A novel approach for the design and synthesis of membrane separation systems has been developed. The theory is shown to be applicable to both batch and continuous membrane operations, and has been formulated in such a way that it is valid for any type of membrane. In this thesis, however, only vapour permeation and pervaporation membranes are incorporated for illustration purposes. The method, which employs a graphical technique, allows one to calculate and visualise the change in composition of the retentate. An integral part of the approach was the derivation of the Membrane Residue Curve Map (M-RCM), and the related differential material balance which describes it. By definition, this plot shows the change, in time, of the retentate composition in a batch still. However, it has been shown that the M-RCM is applicable to conventional continuously-operated membrane units, as well as infinite reflux membrane columns. Finite reflux columns and cascades have been examined by using column sections (CS): any column, or arrangement, no matter how complex, can be broken down into smaller units, namely CS. The development of the Difference Point Equation (DPE) for non-constant flow allowed one to generate, and interpret, profiles for individual CS’s, which can ultimately be connected to form a membrane column arrangement. The profiles, which are more complex than those obtained in the M-RCM, exhibit a unique behavior. Since there is varying flow, the reflux is continually changing, orientating the profile so as to seek a stable node that is “mobile”. Thus, the movement of CS profile is dictated by the location and direction of the pinch point locus. Finally, having membrane permeators examined in an analogous manner to other separation methods, allows for easy synthesis and design of combinations of different processes. Hybrid distillation-membrane systems are analyzed by incorporating CS’s and the appropriate DPE’s which describe each. Investigating the arrangement as a thermally-coupled column introduces a novel way of synthesizing hybrids. Regions of feasibility, which are dictated by the relevant pinch point loci of each separation method, are ultimately sought.

BACKGROUND: Differences in disease-modifying therapy (DMT) prescribing patterns between different groups of neurologists have not been explored. HYPOTHESIS: MS-specialist neurologists use a broader range of DMTs in contrast to generalist neurologists who preferentially prescribe Avonex. METHODS: Ontario neurologist demographic and geographical characteristics were linked to 2009 DMT prescription data. Lorenz curves and Gini coefficients were constructed to examine prescribing patterns; separating neurologist characteristics dichotomously and separating Avonex from the other DMTs. Gini Coefficients were compared using jack-knife statistical techniques to derive 95% confidence intervals. RESULTS: Prescriptions are highly concentrated with 12% of Ontario neurologists prescribing 80% of DMTs. High-volume prescribers show a broader range of DMT use while low-volume prescribers tend to use a particular DMT. CONCLUSIONS: The majority of DMTs are prescribed by a small subset of neurologists. High-volume prescribers show more variability in DMT use while low-volume prescribers tend to individually focus on a narrower range of DMTs.

BACKGROUND: Differences in disease-modifying therapy (DMT) prescribing patterns between different groups of neurologists have not been explored. HYPOTHESIS: MS-specialist neurologists use a broader range of DMTs in contrast to generalist neurologists who preferentially prescribe Avonex. METHODS: Ontario neurologist demographic and geographical characteristics were linked to 2009 DMT prescription data. Lorenz curves and Gini coefficients were constructed to examine prescribing patterns; separating neurologist characteristics dichotomously and separating Avonex from the other DMTs. Gini Coefficients were compared using jack-knife statistical techniques to derive 95% confidence intervals. RESULTS: Prescriptions are highly concentrated with 12% of Ontario neurologists prescribing 80% of DMTs. High-volume prescribers show a broader range of DMT use while low-volume prescribers tend to use a particular DMT. CONCLUSIONS: The majority of DMTs are prescribed by a small subset of neurologists. High-volume prescribers show more variability in DMT use while low-volume prescribers tend to individually focus on a narrower range of DMTs.

Analysts increasingly have used probabilistic approaches to evaluate the uncertainty in reserves estimates based on a decline curve analysis. This is because the results represent statistical analysis of historical data that usually possess significant amounts of noise. Probabilistic approaches usually provide a distribution of reserves estimates with three confidence levels (P10, P50 and P90) and a corresponding 80% confidence interval. The question arises: how reliable is this 80% confidence interval? In other words, in a large set of analyses, is the true value of reserves contained within this interval 80% of the time? Our investigation indicates that it is common in practice for true values of reserves to lie outside the 80% confidence interval much more than 20% of the time using traditional statistical analyses. This indicates that uncertainty is being underestimated, often significantly. Thus, the challenge in probabilistic reserves estimation using a decline curve analysis is not only how to appropriately characterize probabilistic properties of complex production data sets, but also how to determine and then improve the reliability of the uncertainty quantifications. This thesis presents an improved methodology for probabilistic quantification of reserves estimates using a decline curve analysis and practical application of the methodology to actual individual well decline curves. The application of our proposed new method to 100 oil and gas wells demonstrates that it provides much wider 80% confidence intervals, which contain the true values approximately 80% of the time. In addition, the method yields more accurate P50 values than previously published methods. Thus, the new methodology provides more reliable probabilistic reserves estimation, which has important impacts on economic risk analysis and reservoir management.

Signal-to-noise ratio (SNR) estimation is one of the important research topics in wireless communications. In the receiver, many algorithms require SNR information to achieve optimal performance. In this thesis, an autocorrelation based SNR estimator is proposed. The proposed method utilizes the correlation properties of symbol sequence and the uncorrelated properties of noise sequence to distinguish the signal power from the received signal. Curve fitting method is used for SNR estimator to predict the signal power. Mean and variance performance of the proposed SNR estimator is compared with that of the conventional SNR estimator by computer simulations. These simulations consider additive white Gaussian noise and multipath Rayleigh fading channel with BPSK, 8PSK, 16QAM and 64QAM modulation schemes. According to the simulation results, the proposed method can provide better performance than conventional methods in both mean and mean-square-error.

Thesis (Ph. D.)--University of Oregon, 2000. / Typescript. Includes vita and abstract. Includes bibliographical references (leaves 143-145). Also available for download via the World Wide Web; free to University of Oregon users.

Geosynthetic clay liners (GCL) are a composite material commonly used as hydraulic barriers in landfill liners. Due to their dependence on hydration for proper function, the water retention curve (WRC) of a GCL is important. The inherent difficulty in obtaining the WRC, including the range of suction and composite material, has limited the number of GCL WRCs in the literature. In order to quantify the large range of suctions, a dual testing technique was developed, which uses a high capacity tensiometer to measure suctions for the low suction range (0 - 500 kPa) and a relative humidity sensor for the high suction range (3,000 - 1,000,000 kPa). In total, four different GCL products were tested, varying in both materials (woven and nonwoven geotextiles) and construction methods (thermal treatment and needle punching). The dual technique method was used to establish both wetting and drying curves that were presented as gravimetric, volumetric and bulk GCL void ratio WRCs. The WRCs of the different GCL products showed significant variation between their wetting and drying curves indicating that both needle punching and thermal treatment have a significant effect on the swelling behaviour of the GCL and its WRC. Theoretical equations were fit to the experimental data establishing the parameters that can be used for numerical modeling of these four GCL products. / Thesis (Master, Civil Engineering) -- Queen's University, 2009-04-22 14:37:55.196