No description available.

No description available.

No description available.

No description available.

This thesis studies the problem of frequentist model averaging over a set of multiple $\epsilon$-support vector regression (SVR) models, where the support vector machine (SVM) algorithm was extended to function estimation involving continuous targets, instead of categorical ones. By assigning weights to a set of candidate models instead of selecting the least misspecified one, model averaging presents a strong alternative to model selection for tackling model uncertainty. Not only do we describe the construction of smoothed BIC/AIC model averaging weights, but we also propose a Mallows model averaging procedure which selects model weights by minimizing Mallows' criterion. We conduct two studies where the set of candidate models can either include or not include the true model by making use of simulated random samples obtained from different data-generating processes of analytic form. In terms of mean squared error, we demonstrate that our proposed method outperforms other model averaging and model selection methods that were tested, and the gain is more substantial for smaller sample sizes with larger signal-to-noise ratios. / Thesis / Master of Science (MSc)

No description available.

A hierarchical approach is typically followed in design of consumer products. First, a manufacturer sets performance targets for the whole system according to customer surveys and benchmarking of competitors' products. Then, designers cascade these targets to the subsystems or the components using a very simplified model of the overall system. Then, they try to design the components so that they meet these targets. It is important to have efficient tools that check if a set of performance targets for a component corresponds to a feasible design and determine the dimensions and mass of this design. This dissertation presents a methodology for developing two tools that link performance targets for a design to design variables that specify the geometry of the design. The first tool (called translator A) predicts the stiffness and mass of an automotive joint, whose geometry is specified, almost instantaneously. The second tool (called translator B) finds the most efficient, feasible design whose performance characteristics are close to given performance targets. The development of the two translators involves the following steps. First, an automotive joint is parameterized. A set of physical parameters are identified that can completely describe the geometry of the joint. These parameters should be easily understood by designers. Then, a parametric model is created using a CAD program, such as Pro/Engineer or I-Deas. The parametric model can account for different types of construction, and includes relations for styling, packaging, and manufacturing constraints. A database is created for each joint using the results from finite element analysis of hundreds or thousands of joint designs. The elements of the database serve as examples for developing Translator A. Response surface polynomials and neural networks are used to develop translator A. Stepwise regression is used in this study to rank the design variables in terms of importance and to obtain the best regression model. Translator B uses optimization to find the most efficient design. It analyzes a large number of designs efficiently using Translator A. The modified feasible direction method and sequential linear programming are used in developing translator B. The objective of translator B is to minimize the mass of the joint and the difference of the stiffness from a given target while satisfying styling, manufacturing and packaging constraints. The methodologies for Translators A and B are applied to the B-pillar to rocker and A-pillar to roof rail joints. Translator B is demonstrated by redesigning two joints of actual cars. Translator B is validated by checking the performance and mass of the optimum designs using finite element analysis. This study also compares neural networks and response surface polynomials. It shows that they are almost equally accurate when they are used in both analysis and design of joints. / Ph. D.

One form of model robust regression (MRR) predicts mean response as a convex combination of a parametric and a nonparametric prediction. MRR is a semiparametric method by which an incompletely or an incorrectly specified parametric model can be improved through adding an appropriate amount of a nonparametric fit. The combined predictor can have less bias than the parametric model estimate alone and less variance than the nonparametric estimate alone. Additionally, as shown in previous work for uncorrelated data with linear mean function, MRR can converge faster than the nonparametric predictor alone. We extend the MRR technique to the problem of predicting mean response for clustered non-normal data. We combine a nonparametric method based on local estimation with a global, parametric generalized estimating equations (GEE) estimate through a mixing parameter on both the mean scale and the linear predictor scale. As a special case, when data are uncorrelated, this amounts to mixing a local likelihood estimate with predictions from a global generalized linear model. Cross-validation bandwidth and optimal mixing parameter selectors are developed. The global fits and the optimal and data-driven local and mixed fits are studied under no/some/substantial model misspecification via simulation. The methods are then illustrated through application to data from a longitudinal study. / Ph. D.

Faculty members are influenced by a complex set of factors when making decisions about when to retire. These factors generally include both financial and non-financial characteristics. This study was designed to examine the non-financial factors related to the retirement process for selected faculty groups. Key components of the design included selecting faculty groups for analysis and identifying the non-financial factors related to the retirement process. Two faculty groups were selected: (a) faculty who had previously retired from another position and (b) faculty members with no plans to retire in the next three years. The non-financial factors were identified through a review of the literature and included (a) employment characteristics, (b) demographic characteristics, (c) activity measures, and (d) satisfaction items. The study was based on secondary analysis of NSOPF: 99 data. A combination of descriptive statistics and logistic regression was used to analyze the data. Major findings include (a) previously retired faculty members may be a substantial pool of qualified, productive talent intrinsically motivated to be part of an academic environment on a part-time basis because their financial status is not solely dependent on basic salary from the institution; (b) additional indicators distinguishing age at retirement from a career position versus age at retirement from all paid employment may also be needed to fully describe the issue; (c) employment status, years in current position, program area, age, gender, geographic region, average class size, and satisfaction with other aspects of the job (excluding instructional duties) were distinguishing characteristics of previously retired faculty members; (d) a sizeable portion of older faculty has not yet reached traditional retirement age; (e) the impact of uncapping mandatory retirement ages for tenured faculty may not have yet been fully realized — even eight years after the legislation took effect; (f) evidence does not support some of the objections from the higher education community in opposition to uncapping; and (g) control of institution, program area, years in current position, age, marital status, number of dependents, recent publications, career publications, and satisfaction were distinguishing characteristics of faculty members with no plans to retire in the next three years. / Ph. D.

In this dissertation, we consider two important problems pertaining to the analysis of transportation systems. The first of these is an approach-dependent, time-dependent, label-constrained shortest path problem that arises in the context of the Route Planner Module of the Transportation Analysis Simulation System (TRANSIMS), which has been developed by the Los Alamos National Laboratory for the Federal Highway Administration. This is a variant of the shortest path problem defined on a transportation network comprised of a set of nodes and a set of directed arcs such that each arc has an associated label designating a mode of transportation, and an associated travel time function that depends on the time of arrival at the tail node, as well as on the node via which this node was approached. The lattermost feature is a new concept injected into the time-dependent, label-constrained shortest path problem, and is used to model turn-penalties in transportation networks. The time spent at an intersection before entering the next link would depend on whether we travel straight through the intersection, or make a right turn at it, or make a left turn at it. Accordingly, we model this situation by incorporating within each link's travel time function a dependence on the link via which its tail node was approached. We propose two effective algorithms to solve this problem by adapting two efficient existing algorithms to handle time dependency and label constraints: the Partitioned Shortest Path (PSP) algorithm and the Heap-Dijkstra (HP-Dijkstra) algorithm, and present related theoretical complexity results. In addition, we also explore various heuristic methods to curtail the search. We explore an Augmented Ellipsoidal Region Technique (A-ERT) and a Distance-Based A-ERT, along with some variants to curtail the search for an optimal path between a given origin and destination to more promising subsets of the network. This helps speed up computation without sacrificing optimality. We also incorporate an approach-dependent delay estimation function, and in concert with a search tree level-based technique, we derive a total estimated travel time and use this as a key to prioritize node selections or to sort elements in the heap. As soon as we reach the destination node, while it is within some p% of the minimum key value of the heap, we then terminate the search. We name the versions of PSP and HP-Dijkstra that employ this method as Early Terminated PSP (ET-PSP) and Early Terminated Heap-Dijkstra (ETHP-Dijkstra) algorithms. All of these procedures are compared with the original Route Planner Module within TRANSIMS, which is implemented in the Linux operating system, using C++ along with the g++ GNU compiler. Extensive computational testing has been conducted using available data from the Portland, Oregon, and Blacksburg, Virginia, transportation networks to investigate the efficacy of the developed procedures. In particular, we have tested twenty-five different combinations of network curtailment and algorithmic strategies on three test networks: the Blacksburg-light, the Blacksburg-full, and the BigNet network. The results indicate that the Heap-Dijkstra algorithm implementations are much faster than the PSP algorithmic approaches for solving the underlying problem exactly. Furthermore, mong the curtailment schemes, the ETHP-Dijkstra with p=5%, yields the best overall results. This method produces solutions within 0.37-1.91% of optimality, while decreasing CPU effort by 56.68% at an average, as compared with applying the best available exact algorithm. The second part of this dissertation is concerned with the Classification and Regression Tree (CART) algorithm, and its application to the Activity Generation Module of TRANSIMS. The CART algorithm has been popularly used in various contexts by transportation engineers and planners to correlate a set of independent household demographic variables with certain dependent activity or travel time variables. However, the algorithm lacks an automated mechanism for deriving classification trees based on optimizing specified objective functions and handling desired side-constraints that govern the structure of the tree and the statistical and demographic nature of its leaf nodes. Using a novel set partitioning formulation, we propose new tree development, and more importantly, optimal pruning strategies to accommodate the consideration of such objective functions and side-constraints, and establish the theoretical validity of our approach. This general enhancement of the CART algorithm is then applied to the Activity Generator module of TRANSIMS. Related computational results are presented using real data pertaining to the Portland, Oregon, and Blacksburg, Virginia, transportation networks to demonstrate the flexibility and effectiveness of the proposed approach in classifying data, as well as to examine its numerical performance. The results indicate that a variety of objective functions and constraints can be readily accommodated to efficiently control the structural information that is captured by the developed classification tree as desired by the planner or analyst, dependent on the scope of the application at hand. / Ph. D.