Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 25 for “"Distribution regression"”.
-
Efficient Distribution Regression
In this thesis we devise a method for performing distribution regression utilizing an extension of mixture density networks. This method will be benchmarked against other state-of-the-art methods (utilizing negative log loss) and distribution-agnostic models of similar complexity. We demonstrate …
-
Distribution Regression: Theory and Application
In this dissertation we discuss the problem of distribution regression. That is, the problem of utilizing distributional covariates in predicting scalar outcomes. We first show an application in neuroimaging that relates functional connectivity measurements viewed as statistical distributions to …
-
Essays in econometrics and distributional analysis
… explore the intersection of causal inference and distributional analysis using observational data. The first two chapters develop and apply econometric tools to measure heterogeneous treatment effects of policy interventions and the third chapter proposes a unified approach to distribution …
-
ESSAYS ON MICROECONOMETRICS AND LABOR ECONOMICS
… income mobility and the application of distributional decomposition to income inequality. The first two chapters propose semiparametric distribution regression estimators to study the transition matrices and local rank-rank slopes which are two measures of intergenerational income …
-
Path Signature-Based Machine Learning Methods Applied to Quantitative Finance
… tasks; two-sample hypothesis testing and distribution regression.<br/><br/>Maximum mean discrepancy (MMD) is a kernel-based method for comparing finite-dimensional distributions. Using the signature kernel, the MMD can be applied to path-space valued distributions (sig-MMD) and therefore …
-
Simulation Study on Count Data Based on Double Poisson Distribution
This thesis delves into the double Poisson distribution. Regression based on the double Poisson distribution, as proposed by Efron in 1986, offers an alternative approach that allows for more accurate regression models when dealing with discrete data that exhibit either over- or under-dispersion …
-
Essays on panel data and sample selection methods
… heterogeneity. In Chapter 1, I develop a distribution regression model with sample selection for panel and network data. The model is a semiparametric generalization of the HSM that accommodates much richer patterns of heterogeneity in the selection process, covariates and unobserved …
-
A COMPACT NETWORK MODEL FOR LEARNING IN DISTRIBUTION SPACE
… various tasks, challenges remain in the area of regression on function spaces. In this thesis, we address the problem of regression where the data are distributions. However, neural networks are not designed for distribution inputs - the networks are unable to encode function inputs compactly as …
-
ESSAYS ON HETEROGENEOUS TREATMENT EFFECTS IN THE LABOR MARKET
… States, while the second chapter studies the distributional effects of job displacement using quantile regression and distribution regression. The third chapter considers the distributional effects of having children on women's income. In particular, I apply the Changes in Changes approach and …
-
Evaluation Of The Current State Of Florida West Nile Surveillance Program As A Predictor For Control And Prevention Of Human West Nile Diseases
… graphs, spatial information, correlations and regression models. Data for sentinel chickens, bird necropsy and mosquito pool surveillance from participating counties in Florida were obtained from the State of Florida surveillance database. The human data was obtained from the State of Florida …
-
Sliced optimal transport in Bayesian inference
… transport. Modern applications often involve distributions of diverse forms, in high dimensions, or with large-scale samples, motivating the development of Bayesian inference procedures that operate directly on distributions. The first chapter of this dissertation reviews the foundations of …
-
Rough paths, kernels, differential equations and an algebra of functions on streams
… <p>Chapter 2: Distribution Regression refers to the supervised learning problem where inputs are probability distributions (or some samples) and outputs are scalars. In practice it can be used to address situations where labels are only available for groups of …
-
Essays in labour economics
… A notable extension quantifies the magnitude and distributional impact of spillover effects linked to minimum wages and the threat effects of unionization. A distribution regression framework is used to estimate both types of spillover effects. Accounting for spillover effects doubles the …
-
Estimation of Policy Effects and Counterfactual Distributions: An Application to Food Security Analysis in Mexico
… methodological breakthrough in this field named distribution regression and to use it conjointly with causal analysis, to estimate the effects of a policy. The novelty relies in the estimation not only of the expectation of the difference between observed and counterfactual outcome, the usual …
-
Psichoemocinių veiksnių sąsajos su dantų ėduonimi pacientų su įvairiomis burnos sausumo būklėmis imtyje /
… Spearman correlation and negative binomial distribution regression analysis were applied. The result was considered statistically significant if p < 0.05. Results: There were 121 participants in the study, more of which were women (N = 101, 84%) than men (N = 19, 16 %). Age and DMFS index …
-
Three essays on microeconometrics
… covariates. The second chapter examines distributional heterogeneity in selection patterns in sample selection models. Lastly, the third chapter develops a censored quantile regression model with high-dimensional control variables to estimate quantile-specific heterogeneity in censored …
-
Išorinių ir vidinių veiksnių įtaka aplinkosauginiam laboratorijų rezultatyvumui, medijuojant aplinkosaugos vadybos brandai /
… - descriptive statistics are presented, data distribution is checked according to the normal distribution, regression models are presented, mediation analysis is performed. Finally, the results of the empirical research, conclusions, suggestions, and limitations of the research are summarized. …
-
On the properties of random feature methods
… property is valid for both kernel ridge regression and distribution regression settings.</p> <p>Next, we explore the computation and statistical accuracy trade-off of random feature methods. We provide the first unified risk analysis of learning with random feature approximation for both …
-
Approximating Bayesian Optimal Sequential Designs using Gaussian Process Models Indexed on Belief States
… underlying geometry of the space of probability distributions. We propose the use of Gaussian process models indexed on the belief states visited in experimentation to provide utility-agnostic surrogate models for approximating Bayesian optimal sequential designs which require no feature …
-
ESSAYS ON MICROECONOMETRICS AND FINANCE
… establish estimators which are useful to study distributional effects of a continuous treatment and local elasticities, respectively. The tools then are applied on to intergenerational income mobility. Thus, Chapter 1 and 2 are on Microeconomics. Chapter 3 and 4 are on Finance. In particular, I …
Page 1 of 2