No description available.

No description available.

This study examined the use of ranking task exercises in physics as a means to elicit student's quantitative and/or qualitative understanding of four different physics concepts. Each ranking task exercise in physics asked students to examine several different scenarios that contain a number of quantitative features and then arrange the scenarios in an ordered sequence according to some other quantitative feature. In this study, students completed four different ranking task exercises as part of their coursework in their high school physics class. The responses of students to these ranking task exercises were scored, analyzed, and categorized according to the extent to which a student's response was primarily quantitative or primarily qualitative in nature. The results show that while students relied on a combination of both qualitative and quantitative representations as they completed the exercises, the majority of students used qualitative representations in their solutions to the ranking task exercises in physics. While the students' qualitative and quantitative representations supported the students' rankings of the scenarios in each ranking task exercise, the qualitative representations used by the students provided insight into the student's current understanding of the physics concepts being investigated. The findings suggest that regardless of the representation used by the student to complete the ranking task exercise, students had difficulty in correctly ranking the scenarios in all of the ranking task exercises used in this study. While the students used both quantitative and qualitative representations in their solutions to ranking task exercises in physics that contained two quantitative variables, the study found that students relied exclusively on qualitative representations in their solutions to the ranking task exercise in physics that contained four quantitative variables. / CITE/Mathematics and Science Education

Background and Objectives: Understanding patient and public values and preferences is essential to healthcare and policy decision making. Discrete choice experiments (DCEs) are a common tool used to capture and quantify these preferences. Recent technological advances allow for a variety of approaches to create and analyze DCEs. However, there is no optimal DCE design, nor analysis method. Our objectives were to (i) survey DCE simulation studies to determine what design features affect statistical efficiency, and assess their reporting, (ii) further investigate these findings with a de novo simulation study, and (iii) explore the sensitivity of individuals’ preference of attributes to several methods of analysis. Methods: We conducted a systematic survey of simulation studies within the health literature, created a DCE simulation study of 3204 designs, and performed two empirical comparison studies. In one empirical comparison study, we determined addiction agency employees’ preferences on knowledge translation attributes using four models, and in the second, we determined elementary school children’s choice of bullying prevention programs using nine models. Results and Conclusions: In our evaluation of DCE designs, we identified six design features that impact the statistical efficiency of a DCE, several of which were further investigated in our simulation study. The reporting quality of these studies requires improvement to ensure that appropriate inferences can be made, and that they are reproducible. In our empirical comparison of statistical models to explore the sensitivity of individuals preferences of attributes, we found similar rankings in the relative importance measures of attributes’ mean part-worth utility estimates, which differed when using latent class models. Understanding the impact of design features on statistical efficiency are useful for designing optimal DCEs. Incorporating heterogeneity in the analysis of DCEs may be important to make appropriate inferences about individuals’ preferences of attributes within a population. / Thesis / Doctor of Philosophy (PhD) / This thesis focuses on the design and analysis of preference surveys, which are referred to as discrete choice experiments. These surveys are used to capture and quantify individuals’ preferences on various characteristics describing a product or service. They are applied in various health settings to better understand a population. For example, clinicians may want to further understand a patient population’s preferences in regards to multiple treatment alternatives. Currently, there is no optimal approach for designing or analyzing preference surveys. We investigated what factors help improve the design of a preference survey by exploring the literature and conducting our own simulation study. We also investigated how sensitive the results of a preference survey were based on the statistical model used. Overall, we found that (i) increasing the amount of information presented and reducing the number of variables to explore will maximize the statistical optimality of the survey; and (ii) analyzing the data with different statistical models will yield similar results in the ranking of individuals’ preferences of the variables explored.

Some classes of Internet users have specific information needs and specialized information-seeking behaviors. For example, educators who are designing a course might create a syllabus, recommend books, create lecture slides, and use tools as lecture aid. All of these resources are available online, but are scattered across a large number of websites. Collecting, linking, and presenting the disparate items related to a given course topic within a digital library will help educators in finding quality educational material. Content quality is important for users. The results of popular search engines typically fail to reflect community input regarding quality of the content. To disseminate information related to the quality of available resources, users need a common place to meet and share their experiences. Online communities can support knowledge-sharing practices (e.g., reviews, ratings). We focus on finding the information needs of educators and helping users to identify potentially useful resources within an educational digital library. This research builds upon the existing 5S digital library (DL) framework. We extend core DL services (e.g., index, search, browse) to include information from latent user groups. We propose a formal definition for the next generation of educational digital libraries. We extend one aspect of this definition to study methods that incorporate collective knowledge within the DL framework. We introduce the concept of deduced social network (DSN) - a network that uses navigation history to deduce connections that are prevalent in an educational digital library. Knowledge gained from the DSN can be used to tailor DL services so as to guide users through the vast information space of educational digital libraries. As our testing ground, we use the AlgoViz and Ensemble portals, both of which have large collections of educational resources and seek to support online communities. We developed two applications, ranking of search results and recommendation, that use the information derived from DSNs. The revised ranking system incorporates social trends into the system, whereas the recommendation system assigns users to a specific group for content recommendation. Both applications show enhanced performance when DSN-derived information is incorporated. / Ph. D.

While existing off-policy evaluation (OPE) methods typically estimate the value of a policy, in real-world applications, OPE is often used to compare and rank policies before deploying them in the real world. This is also known as the offline policy ranking problem. While one can rank the policies based on point estimates from OPE, it is beneficial to estimate the full distribution of outcomes for policy ranking and selection. This paper introduces Probabilistic Offline Policy Ranking that works with expert trajectories. It introduces rigorous statistical inference capabilities to offline evaluation, which facilitates probabilistic comparisons of candidate policies before they are deployed. We empirically demonstrate that POPR is effective for evaluating RL policies across various environments.

A method is presented for analysing a 2 x 2 factorial experiment in which the data consist cf relative rankings in pairwise comparisons. Maximum likelihood estimates are developed for the ratings of the various levels of each factor und for the treatment combinations. Likelihood ratio tests of the most important hypotheses likely to arise are derived in detail. The large sample approximations are used. In addition, the method is presented in a manner such that tests of other hypotheses in which the experimenter might be interested can easily be derived. The equations for the analysis of a factorial design of arbitrary size are presented, It can be seen, however, that the complexity of these equations render an attempt at their solution impractical in most cases and more work must be done if a useful method of analysing experiments of this, type is to be found. / Master of Science

With increased pressures from governmental and insurance agencies, today's physician devotes less time to patient care and more time to administration. To alleviate this problem, Biological & Popular Culture, Inc. (Biopop) proposed the building of partnerships with healthcare professionals to provide high-quality, cost-effective medical care in a physician network setting. To assist Biopop in evaluating potential operating procedures, a discrete-event simulation model has been constructed. The model is built in an object-oriented, visual manner utilizing the Visual Simulation Environment (VSE). The model examines both internal Biopop operations and external clinic operations. The research presented herein describes the design of the simulation model and details the analysis of the clinical environment. A methodology for determining appropriate staffing and physical resources in a clinical environment is presented. This methodology takes advantage of several simulation-based statistical techniques, including batch means; fractional factorial design; and simultaneous ranking, selection, and multiple comparisons. An explanation of the experimental design is provided and results of the experimentation are presented. Based upon the experimental results, conclusions are drawn and recommendations are made for an appropriate staffing and facility size for a two-physician family practice healthcare clinic. / Master of Science

In this study 64 web based services (bibliographical, patron education, patron communication and patron publication services) and best practices offered by the 70 top world university libraries and 39 top Indian University libraries were studied using different data analysis techniques like cross-tabulating for average scores and Pearson correlation coefficient and tests like Chi-Square Test and T-Test were applied to the raw data collected for final results. The library rankings as per their web-based services were correlated with their university rankings as per Webometric rankings and found that library web-based services rankings are correlating with their university rankings. Therefore, developing countries like India should improve their library web-based services rankings to improve their rankings at global level. / Doctor of Philosophy

This thesis gathers some contributions to statistical pattern recognition particularly targeted at problems in which the feature vectors are high-dimensional. Three pattern recognition scenarios are addressed, namely pattern classification, regression analysis and score fusion. For each of these, an algorithm for learning a statistical model is presented. In order to address the difficulty that is encountered when the feature vectors are high-dimensional, adequate models and objective functions are defined. The strategy of learning simultaneously a dimensionality reduction function and the pattern recognition model parameters is shown to be quite effective, making it possible to learn the model without discarding any discriminative information. Another topic that is addressed in the thesis is the use of tangent vectors as a way to take better advantage of the available training data. Using this idea, two popular discriminative dimensionality reduction techniques are shown to be effectively improved. For each of the algorithms proposed throughout the thesis, several data sets are used to illustrate the properties and the performance of the approaches. The empirical results show that the proposed techniques perform considerably well, and furthermore the models learned tend to be very computationally efficient. / Villegas Santamaría, M. (2011). Contributions to High-Dimensional Pattern Recognition [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/10939