Theses and Dissertations from UMD
Permanent URI for this communityhttp://hdl.handle.net/1903/2
New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
3 results
Search Results
Item STATISTICAL METHODS FOR ADVANCED ECONOMETRIC MODELS WITH APPLICATIONS TO VEHICLE HOLDING AND SPEED QUANTILES DISTRIBUTION(2016) Tremblay, Jean-Michel; Cirillo, Cinzia; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)This dissertation proposes statistical methods to formulate, estimate and apply complex transportation models. Two main problems are part of the analyses conducted and presented in this dissertation. The first method solves an econometric problem and is concerned with the joint estimation of models that contain both discrete and continuous decision variables. The use of ordered models along with a regression is proposed and their effectiveness is evaluated with respect to unordered models. Procedure to calculate and optimize the log-likelihood functions of both discrete-continuous approaches are derived, and difficulties associated with the estimation of unordered models explained. Numerical approximation methods based on the Genz algortithm are implemented in order to solve the multidimensional integral associated with the unordered modeling structure. The problems deriving from the lack of smoothness of the probit model around the maximum of the log-likelihood function, which makes the optimization and the calculation of standard deviations very difficult, are carefully analyzed. A methodology to perform out-of-sample validation in the context of a joint model is proposed. Comprehensive numerical experiments have been conducted on both simulated and real data. In particular, the discrete-continuous models are estimated and applied to vehicle ownership and use models on data extracted from the 2009 National Household Travel Survey. The second part of this work offers a comprehensive statistical analysis of free-flow speed distribution; the method is applied to data collected on a sample of roads in Italy. A linear mixed model that includes speed quantiles in its predictors is estimated. Results show that there is no road effect in the analysis of free-flow speeds, which is particularly important for model transferability. A very general framework to predict random effects with few observations and incomplete access to model covariates is formulated and applied to predict the distribution of free-flow speed quantiles. The speed distribution of most road sections is successfully predicted; jack-knife estimates are calculated and used to explain why some sections are poorly predicted. Eventually, this work contributes to the literature in transportation modeling by proposing econometric model formulations for discrete-continuous variables, more efficient methods for the calculation of multivariate normal probabilities, and random effects models for free-flow speed estimation that takes into account the survey design. All methods are rigorously validated on both real and simulated data.Item DISCRETE CHOICE UNDER SPATIAL DEPENDENCE AND A MODEL OF INTERDEPENDENT PATENT RENEWALS(2011) Iercosan, Diana A.; Prucha, Ingmar; Economics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)In my thesis I develop a theoretical model of interdependent choices and an estimation strategy which I apply to model patent renewal. The model and the estimation are not confined to my application, but rather can have other applications in which firms or people are making strategic and simultaneous decisions. Chapter 1 is the introduction which contains a brief description of the structure of the thesis. Chapter 2 provides a literature review of studies that have focused on spatial dependence with discrete choice dependent variables; recent contributions include Pinkse and Slade (1998), LeSage (2000), Kelejian and Prucha (2001), Beron and Vijverberg (2004), and Wang et al. (2009). A major difficulty in the estimation of spatially dependent discrete choice models is computational intensity. Chapter 3 is a Monte Carlo study that investigates the small sample properties of an estimator for spatially dependent discrete choice models which is computationally simple. The analogue of a linear probability can be formulated as a spatial autoregressive Cliff and Ord (1973, 1981)-type model. The sets of Monte Carlo experiments show that the parameters of the model can be estimated without bias using a spatial 2SLS estimator. Chapter 4 is a study is on the determinants of patent renewal, using US patents for Computer Hardware and Software granted between 1994 and 1997. Patent protection is important in that it encourages innovation by allowing firms to rely on patents to appropriate the returns to their R&D efforts. Returns to patents are modeled to depend on the firm's willingness to pay the patent renewal fees by, e.g., Harhoff et al. (2003), Serrano (2006), and Bessen (2008, 2009), and typically ignored potential interdependences in the decision making. Liu et al. (2008) showed that patent renewal was more likely if the patent was part of a firm's sequence of citing patents. I elaborate on their result and formulate a model in which the decision to renew a patent is dependent on the decisions of other firms to renew technologically similar patents. The theoretical model implies for the probability to renew a patent to depend on the probabilities to renew other patents, where the extent of interdependence is modeled based on a measure of similarity for patents. By making use of the estimation strategy from Chapter 3, I find that indeed the decision to renew a patent is dependent on the decision to renew related patents. Results in the literature which ignored this interdependence may hence suffer from specification biases. One plausible explanation for the interdependence I find is defensive patenting in the form of patent fencing, patent blocking and patent thickets. In the latter case, litigation and negotiation can impose high costs to society and their anticipation can lead to a hold up problem, which could deter investment in R&D.Item Evaluating the Equilibrium Welfare Impacts of the 1990 Clean Air Act Amendments in the Los Angeles Area(2007-07-16) TRA, CONSTANT I; McConnell, Kenneth E; Bento, Antonio M; Agricultural and Resource Economics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)This dissertation develops a discrete choice equilibrium model to evaluate the benefits of the air quality improvements that occurred in the Los Angeles area following the 1990 Clean Air Act Amendments (CAAA). Large improvements in air quality will change the desirability of different neighborhoods, disrupting the equilibrium of the housing market. The discrete choice equilibrium approach accounts for the fact that air quality improvements brought about by the 1990 CAAA will change housing choices and prices. The dissertation makes two empirical contributions to public economics. First, the study provides the first application of the discrete choice equilibrium framework (Anas, 1982, Bayer et al., 2005) to the valuation of large environmental changes. Second, the study provides new evidence for the distributional benefits of the 1990 CAAA in the Los Angeles area. Households' location choices are modeled according to the random utility framework of McFadden (1978) and the differentiated product specification of Berry, Levinsohn and Pakes (1995). The model is estimated with public-use household microdata from the 1990 U.S. Census. Findings suggest that the air quality improvements that occurred in the Los Angeles area between 1990 and 2000 provided an average equilibrium welfare benefit of $1,800 to households. In contrast, average benefits are $1,400 when equilibrium price effects are not accounted, demonstrating that ignoring equilibrium effects will likely underestimate the benefits of large environmental changes. We find that the equilibrium welfare impacts of the 1990 CAAA in the Los Angeles area varied significantly across income groups. Households in the highest income quartile experienced equilibrium benefits of approximately $3,600 as compared to only $400 for households in the lowest income quartile. We also find that ignoring equilibrium adjustments in housing prices can significantly alter the distribution of relative welfare gains (i.e. welfare gains as a proportion of household income) across households. Indeed, welfare impacts that do not account for equilibrium adjustments suggest that high-income households experience larger relative welfare gains compared to low-income households. However, when accounting for equilibrium adjustments, we find that the distribution of relative welfare gains from the 1990 CAAA is fairly even across income groups.