Matching Items (4)
Filtering by
- All Subjects: mobility
- All Subjects: spatial statistics
- Genre: Academic theses
- Creators: Kang, Yun
Description
As urban populations become increasingly dense, massive amounts of new 'big' data that characterize human activity are being made available and may be characterized as having a large volume of observations, being produced in real-time or near real-time, and including a diverse variety of information. In particular, spatial interaction (SI) data - a collection of human interactions across a set of origins and destination locations - present unique challenges for distilling big data into insight. Therefore, this dissertation identifies some of the potential and pitfalls associated with new sources of big SI data. It also evaluates methods for modeling SI to investigate the relationships that drive SI processes in order to focus on human behavior rather than data description.
A critical review of the existing SI modeling paradigms is first presented, which also highlights features of big data that are particular to SI data. Next, a simulation experiment is carried out to evaluate three different statistical modeling frameworks for SI data that are supported by different underlying conceptual frameworks. Then, two approaches are taken to identify the potential and pitfalls associated with two newer sources of data from New York City - bike-share cycling trips and taxi trips. The first approach builds a model of commuting behavior using a traditional census data set and then compares the results for the same model when it is applied to these newer data sources. The second approach examines how the increased temporal resolution of big SI data may be incorporated into SI models.
Several important results are obtained through this research. First, it is demonstrated that different SI models account for different types of spatial effects and that the Competing Destination framework seems to be the most robust for capturing spatial structure effects. Second, newer sources of big SI data are shown to be very useful for complimenting traditional sources of data, though they are not sufficient substitutions. Finally, it is demonstrated that the increased temporal resolution of new data sources may usher in a new era of SI modeling that allows us to better understand the dynamics of human behavior.
A critical review of the existing SI modeling paradigms is first presented, which also highlights features of big data that are particular to SI data. Next, a simulation experiment is carried out to evaluate three different statistical modeling frameworks for SI data that are supported by different underlying conceptual frameworks. Then, two approaches are taken to identify the potential and pitfalls associated with two newer sources of data from New York City - bike-share cycling trips and taxi trips. The first approach builds a model of commuting behavior using a traditional census data set and then compares the results for the same model when it is applied to these newer data sources. The second approach examines how the increased temporal resolution of big SI data may be incorporated into SI models.
Several important results are obtained through this research. First, it is demonstrated that different SI models account for different types of spatial effects and that the Competing Destination framework seems to be the most robust for capturing spatial structure effects. Second, newer sources of big SI data are shown to be very useful for complimenting traditional sources of data, though they are not sufficient substitutions. Finally, it is demonstrated that the increased temporal resolution of new data sources may usher in a new era of SI modeling that allows us to better understand the dynamics of human behavior.
ContributorsOshan, Taylor Matthew (Author) / Fotheringham, A. S. (Thesis advisor) / Farmer, Carson J.Q. (Committee member) / Rey, Sergio S.J. (Committee member) / Nelson, Trisalyn (Committee member) / Arizona State University (Publisher)
Created2017
Description
In this dissertation the potential impact of some social, cultural and economic factors on
Ebola Virus Disease (EVD) dynamics and control are studied. In Chapter two, the inability
to detect and isolate a large fraction of EVD-infected individuals before symptoms onset is
addressed. A mathematical model, calibrated with data from the 2014 West African outbreak,
is used to show the dynamics of EVD control under various quarantine and isolation
effectiveness regimes. It is shown that in order to make a difference it must reach a high
proportion of the infected population. The effect of EVD-dead bodies has been incorporated
in the quarantine effectiveness. In Chapter four, the potential impact of differential
risk is assessed. A two-patch model without explicitly incorporate quarantine is used to
assess the impact of mobility on communities at risk of EVD. It is shown that the
overall EVD burden may lessen when mobility in this artificial high-low risk society is allowed.
The cost that individuals in the low-risk patch must pay, as measured by secondary
cases is highlighted. In Chapter five a model explicitly incorporating patch-specific quarantine
levels is used to show that quarantine a large enough proportion of the population
under effective isolation leads to a measurable reduction of secondary cases in the presence
of mobility. It is shown that sharing limited resources can improve the effectiveness of
EVD effective control in the two-patch high-low risk system. Identifying the conditions
under which the low-risk community would be willing to accept the increases in EVD risk,
needed to reduce the total number of secondary cases in a community composed of two
patches with highly differentiated risks has not been addressed. In summary, this dissertation
looks at EVD dynamics within an idealized highly polarized world where resources
are primarily in the hands of a low-risk community – a community of lower density, higher
levels of education and reasonable health services – that shares a “border” with a high-risk
community that lacks minimal resources to survive an EVD outbreak.
Ebola Virus Disease (EVD) dynamics and control are studied. In Chapter two, the inability
to detect and isolate a large fraction of EVD-infected individuals before symptoms onset is
addressed. A mathematical model, calibrated with data from the 2014 West African outbreak,
is used to show the dynamics of EVD control under various quarantine and isolation
effectiveness regimes. It is shown that in order to make a difference it must reach a high
proportion of the infected population. The effect of EVD-dead bodies has been incorporated
in the quarantine effectiveness. In Chapter four, the potential impact of differential
risk is assessed. A two-patch model without explicitly incorporate quarantine is used to
assess the impact of mobility on communities at risk of EVD. It is shown that the
overall EVD burden may lessen when mobility in this artificial high-low risk society is allowed.
The cost that individuals in the low-risk patch must pay, as measured by secondary
cases is highlighted. In Chapter five a model explicitly incorporating patch-specific quarantine
levels is used to show that quarantine a large enough proportion of the population
under effective isolation leads to a measurable reduction of secondary cases in the presence
of mobility. It is shown that sharing limited resources can improve the effectiveness of
EVD effective control in the two-patch high-low risk system. Identifying the conditions
under which the low-risk community would be willing to accept the increases in EVD risk,
needed to reduce the total number of secondary cases in a community composed of two
patches with highly differentiated risks has not been addressed. In summary, this dissertation
looks at EVD dynamics within an idealized highly polarized world where resources
are primarily in the hands of a low-risk community – a community of lower density, higher
levels of education and reasonable health services – that shares a “border” with a high-risk
community that lacks minimal resources to survive an EVD outbreak.
ContributorsEspinoza Cortes, Baltazar (Author) / Castillo-Chavez, Carlos (Thesis advisor) / Kang, Yun (Committee member) / Safan, Muntaser (Committee member) / Arizona State University (Publisher)
Created2018
Description
Spatial regression is one of the central topics in spatial statistics. Based on the goals, interpretation or prediction, spatial regression models can be classified into two categories, linear mixed regression models and nonlinear regression models. This dissertation explored these models and their real world applications. New methods and models were proposed to overcome the challenges in practice. There are three major parts in the dissertation.
In the first part, nonlinear regression models were embedded into a multistage workflow to predict the spatial abundance of reef fish species in the Gulf of Mexico. There were two challenges, zero-inflated data and out of sample prediction. The methods and models in the workflow could effectively handle the zero-inflated sampling data without strong assumptions. Three strategies were proposed to solve the out of sample prediction problem. The results and discussions showed that the nonlinear prediction had the advantages of high accuracy, low bias and well-performed in multi-resolution.
In the second part, a two-stage spatial regression model was proposed for analyzing soil carbon stock (SOC) data. In the first stage, there was a spatial linear mixed model that captured the linear and stationary effects. In the second stage, a generalized additive model was used to explain the nonlinear and nonstationary effects. The results illustrated that the two-stage model had good interpretability in understanding the effect of covariates, meanwhile, it kept high prediction accuracy which is competitive to the popular machine learning models, like, random forest, xgboost and support vector machine.
A new nonlinear regression model, Gaussian process BART (Bayesian additive regression tree), was proposed in the third part. Combining advantages in both BART and Gaussian process, the model could capture the nonlinear effects of both observed and latent covariates. To develop the model, first, the traditional BART was generalized to accommodate correlated errors. Then, the failure of likelihood based Markov chain Monte Carlo (MCMC) in parameter estimating was discussed. Based on the idea of analysis of variation, back comparing and tuning range, were proposed to tackle this failure. Finally, effectiveness of the new model was examined by experiments on both simulation and real data.
In the first part, nonlinear regression models were embedded into a multistage workflow to predict the spatial abundance of reef fish species in the Gulf of Mexico. There were two challenges, zero-inflated data and out of sample prediction. The methods and models in the workflow could effectively handle the zero-inflated sampling data without strong assumptions. Three strategies were proposed to solve the out of sample prediction problem. The results and discussions showed that the nonlinear prediction had the advantages of high accuracy, low bias and well-performed in multi-resolution.
In the second part, a two-stage spatial regression model was proposed for analyzing soil carbon stock (SOC) data. In the first stage, there was a spatial linear mixed model that captured the linear and stationary effects. In the second stage, a generalized additive model was used to explain the nonlinear and nonstationary effects. The results illustrated that the two-stage model had good interpretability in understanding the effect of covariates, meanwhile, it kept high prediction accuracy which is competitive to the popular machine learning models, like, random forest, xgboost and support vector machine.
A new nonlinear regression model, Gaussian process BART (Bayesian additive regression tree), was proposed in the third part. Combining advantages in both BART and Gaussian process, the model could capture the nonlinear effects of both observed and latent covariates. To develop the model, first, the traditional BART was generalized to accommodate correlated errors. Then, the failure of likelihood based Markov chain Monte Carlo (MCMC) in parameter estimating was discussed. Based on the idea of analysis of variation, back comparing and tuning range, were proposed to tackle this failure. Finally, effectiveness of the new model was examined by experiments on both simulation and real data.
ContributorsLu, Xuetao (Author) / McCulloch, Robert (Thesis advisor) / Hahn, Paul (Committee member) / Lan, Shiwei (Committee member) / Zhou, Shuang (Committee member) / Saul, Steven (Committee member) / Arizona State University (Publisher)
Created2020
Description
The dissertation addresses questions tied in to the challenges posed by the impact of environmental factors on the nonlinear dynamics of social upward mobility. The proportion of educated individuals from various socio-economic backgrounds is used as a proxy for the environmental impact on the status quo state.
Chapter 1 carries out a review of the mobility models found in the literature and sets the economic context of this dissertation. Chapter 2 explores a simple model that considers poor and rich classes and the impact that educational success may have on altering mobility patterns. The role of the environment is modeled through the use of a modified version of the invasion/extinction model of Richard Levins. Chapter 3 expands the socio-economic classes to include a large middle class to study the role of social mobility in the presence of higher heterogeneity. Chapter 4 includes demographic growth and explores what would be the time scales needed to accelerate mobility. The dissertation asked how long it will take to increase by 22% the proportion of educated from the poor classes under demographic versus non-demographic growth conditions. Chapter 5 summarizes results and includes a discussion of results. It also explores ways of modeling the influence of nonlinear dynamics of mobility, via exogenous factors. Finally, Chapter 6 presents economic perspectives about the role of environmental influence on college success. The framework can be used to incorporate the impact of economic factors and social changes, such as unemployment, or gap between the haves and have nots. The dissertation shows that peer influence (poor influencing the poor) has a larger effect than class influence (rich influencing the poor). Additionally, more heterogeneity may ease mobility of groups but results depend on initial conditions. Finally, average well-being of the community and income disparities may improve over time. Finally, population growth may extend time scales needed to achieve a specific goal of educated poor.
Chapter 1 carries out a review of the mobility models found in the literature and sets the economic context of this dissertation. Chapter 2 explores a simple model that considers poor and rich classes and the impact that educational success may have on altering mobility patterns. The role of the environment is modeled through the use of a modified version of the invasion/extinction model of Richard Levins. Chapter 3 expands the socio-economic classes to include a large middle class to study the role of social mobility in the presence of higher heterogeneity. Chapter 4 includes demographic growth and explores what would be the time scales needed to accelerate mobility. The dissertation asked how long it will take to increase by 22% the proportion of educated from the poor classes under demographic versus non-demographic growth conditions. Chapter 5 summarizes results and includes a discussion of results. It also explores ways of modeling the influence of nonlinear dynamics of mobility, via exogenous factors. Finally, Chapter 6 presents economic perspectives about the role of environmental influence on college success. The framework can be used to incorporate the impact of economic factors and social changes, such as unemployment, or gap between the haves and have nots. The dissertation shows that peer influence (poor influencing the poor) has a larger effect than class influence (rich influencing the poor). Additionally, more heterogeneity may ease mobility of groups but results depend on initial conditions. Finally, average well-being of the community and income disparities may improve over time. Finally, population growth may extend time scales needed to achieve a specific goal of educated poor.
ContributorsMontalvo, Cesar Paul (Author) / Castillo-Chavez, Carlos (Thesis advisor) / Mubayi, Anuj (Thesis advisor) / Perrings, Charles (Committee member) / Kang, Yun (Committee member) / Arizona State University (Publisher)
Created2020