Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorMasson, Virginie-
dc.contributor.authorGarrard, Robert Christopher-
dc.description.abstractThis thesis is comprised of three self-contained essays on econometrics. The frst paper illustrates how stochastic dominance criteria can be used to rank social networks in terms of effciency, and develops statistical in- ference procedures for assessing these criteria. The tests proposed can be viewed as extensions of a Pearson goodness-of-fit test and a studentized maximum modulus test often used to partially rank income distributions and inequality measures. We establish uniform convergence of the empirical size of the tests to the nominal level, and show their consistency under the usual conditions that guarantee the validity of the approximation of a multi- nomial distribution to a Gaussian distribution. Furthermore, we propose a bootstrap method that enhances the finite-sample properties of the tests. The performance of the tests is illustrated via Monte Carlo experiments and an empirical application to risk sharing networks in rural India. The second paper considers the problem of testing a hypothesis H0 : Beta = Beta0 where Beta is a vector representing the degree distribution of a graph and the sample acquired is an induced subgraph. We propose a novel bootstrap procedure to control the size of a test under the null hypothesis by con- structing a graph whose degree distribution conforms to the null hypothesis from which we may draw pseudo-samples in the form of induced subgraphs. We investigate the properties of the bootstrap with a simulation study in which a Wald-type statistic based on a truncated singular value estimator, whose null distribution is approximately chi-square, serves as a benchmark. We then discuss whether this test may be inverted to construct confidence intervals. The third paper presents a selective review of the Lasso estimator as it applies to econometric inference. We survey key papers addressing proper- ties of the Lasso of interest to the econometrician including conditions for consistency, the asymptotic distribution of the estimator, its ability to be bootstrapped, sample splitting for high dimensional inference, and how it may be used to solve the many instruments problem in instrumental variables regression.en
dc.titleEssays in Econometrics with Applications to Social Networksen
dc.contributor.schoolSchool of Economicsen
dc.provenanceThis electronic version is made publicly available by the University of Adelaide in accordance with its open access policy for student theses. Copyright in this thesis remains with the author. This thesis may incorporate third party material which has been used by the author pursuant to Fair Dealing exceptions. If you are the owner of any included third party copyright material you wish to be removed from this electronic version, please complete the take down form located at:
dc.description.dissertationThesis (Ph.D.) -- University of Adelaide, School of Economics, 2017en
Appears in Collections:Research Theses

Files in This Item:
File Description SizeFormat 
Garrard2017_PhD.pdf3.96 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.