Convergence Rates of Spectral Distribution of Random Inner Product Kernel Matrices
AdvisorRider, Brian (Brian C.)
Committee memberYang, Wei-shih, 1954-
Random Geometric Graph
Random Inner Product Kernel Matrix
Permanent link to this recordhttp://hdl.handle.net/20.500.12613/3132
MetadataShow full item record
AbstractThis dissertation has two parts. In the first part, we focus on random inner product kernel matrices. Under various assumptions, many authors have proved that the limiting empirical spectral distribution (ESD) of such matrices A converges to the Marchenko- Pastur distribution. Here, we establish the corresponding rate of convergence. The strategy is as follows. First, we show that for z = u + iv ∈ C, v > 0, the distance between the Stieltjes transform m_A (z) of ESD of matrix A and Machenko-Pastur distribution m(z) is of order O (log n \ nv). Next, we prove the Kolmogorov distance between ESD of matrix A and Marchenko-Pastur distribution is of order O(3\log n\n). It is the less sharp rate for much more general class of matrices. This uses a Berry-Esseen type bound that has been employed for similar purposes for other families of random matrices. In the second part, random geometric graphs on the unit sphere are considered. Observing that adjacency matrices of these graphs can be thought of as random inner product matrices, we are able to use an idea of Cheng-Singer to establish the limiting for the ESD of these adjacency matrices.
ADA complianceFor Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact email@example.com
Showing items related by title, author, creator and subject.
A Nonparametric Test for Deviation from RandomnessIglewicz, Boris; Chitturi, Pallavi; Dong, Yuexiao; Chervoneva, Inna (Temple University. Libraries, 2012)There are many existing tests used to determine if a series consists of a random sample. Often these tests have restrictive distributional assumptions, size distortions, or low power for key useful alternative situations. The interest of this dissertation lies in developing an alternative nonparametric test to determine whether a series consists of a random sample. The proposed test detects deviations from randomness, without a priori distributional assumption, when observations are not independent and identically distributed (i.i.d.), which is suitable for our motivating stock market index data. Departures from i.i.d. are tested by subdividing data into subintervals and then using a conditional probability measure within intervals as a binomial test. This nonparametric test is designed to detect deviations of neighboring observations from randomness when the data set consists of time series observations. Simulation results confirm correct test size for varied distributions and good power for detecting alternative cases. This test is compared to a number of other popular methods and shown to be a competitive alternative. Although the proposed test may be applicable to multiple areas, this dissertation is mostly interested in applications to stock market and regression data. The proposed test is effectively illustrated with the common three stock market index data sets using a newly created transformation, and shown to perform exceptionally well.
Stimulant Reduction Intervention using Dosed Exercise (STRIDE) - CTN 0037: Study protocol for a randomized controlled trialTrivedi, MH; Greer, TL; Grannemann, BD; Church, TS; Somoza, E; Blair, SN; Szapocznik, J; Stoutenberg, M; Rethorst, C; Warden, D; Ring, KM; Walker, R; Morris, DW; Kosinski, AS; Kyle, T; Marcus, B; Crowell, B; Oden, N; Nunes, E; Stoutenberg, Mark|0000-0001-5206-7627 (2011-09-19)Background: There is a need for novel approaches to the treatment of stimulant abuse and dependence. Clinical data examining the use of exercise as a treatment for the abuse of nicotine, alcohol, and other substances suggest that exercise may be a beneficial treatment for stimulant abuse, with direct effects on decreased use and craving. In addition, exercise has the potential to improve other health domains that may be adversely affected by stimulant use or its treatment, such as sleep disturbance, cognitive function, mood, weight gain, quality of life, and anhedonia, since it has been shown to improve many of these domains in a number of other clinical disorders. Furthermore, neurobiological evidence provides plausible mechanisms by which exercise could positively affect treatment outcomes. The current manuscript presents the rationale, design considerations, and study design of the National Institute on Drug Abuse (NIDA) Clinical Trials Network (CTN) CTN-0037 Stimulant Reduction Intervention using Dosed Exercise (STRIDE) study.Methods/Design: STRIDE is a multisite randomized clinical trial that compares exercise to health education as potential treatments for stimulant abuse or dependence. This study will evaluate individuals diagnosed with stimulant abuse or dependence who are receiving treatment in a residential setting. Three hundred and thirty eligible and interested participants who provide informed consent will be randomized to one of two treatment arms: Vigorous Intensity High Dose Exercise Augmentation (DEI) or Health Education Intervention Augmentation (HEI). Both groups will receive TAU (i.e., usual care). The treatment arms are structured such that the quantity of visits is similar to allow for equivalent contact between groups. In both arms, participants will begin with supervised sessions 3 times per week during the 12-week acute phase of the study. Supervised sessions will be conducted as one-on-one (i.e., individual) sessions, although other participants may be exercising at the same time. Following the 12-week acute phase, participants will begin a 6-month continuation phase during which time they will attend one weekly supervised DEI or HEI session. Clinical Trials Registry: ClinicalTrials.gov, NCT01141608. http://clinicaltrials.gov/ct2/show/NCT01141608?term=Stimulant+Reduction+Intervention+using+Dosed+Exercise&rank=1. © 2011 Trivedi et al; licensee BioMed Central Ltd.
A Prospective Randomized Study of the Efficacy of "Turning Point", An Inpatient Violence Intervention ProgramParanjape, Anuradha; Nelson, Deborah B.; Goldberg, Amy (Temple University. Libraries, 2013)Background: From 2002-2011, there were over 17,000 shootings in Philadelphia. "Turning Point", Temple University Hospital's violence intervention program, takes advantage of the teachable moment that occurs after violent injury. In addition to receiving social work services, Turning Point patients watch their trauma bay resuscitation video and a movie about violence, meet with a gunshot wound survivor and an outpatient case manager, and undergo psychiatric assessment. The purpose of this study was to determine the efficacy of Turning Point in changing attitudes toward guns and violence among victims of penetrating trauma. Methods: This prospective randomized study was conducted from January-June 2012. Patients who sustained a gunshot or stab wound were randomized to Standard of Care, which involved social work services only, or Turning Point. The Attitudes Toward Guns and Violence Questionnaire was administered to assess attitude change. Analysis was performed with the Wilcoxon signed-rank test. A p < 0.05 was significant. Results: A total of 40 out of 159 patients with gunshot or stab wounds were enrolled and completed the study in its entirety. The most common reason for exclusion was anticipated length of stay being less than 48 hours. The two groups were similar with respect to most demographics. Unlike the Standard of Care group, the Turning Point group demonstrated a 44% reduction in its Aggressive Response to Shame, a 33% reduction in its Comfort with Aggression, and a 20% reduction in its overall proclivity toward violence. Conclusion: Turning Point is effective in changing attitudes toward guns and violence among victims of penetrating trauma. Continued enrollment and longer follow-up are necessary to determine if this program can have a long-lasting impact and truly be a turning point in patients' lives.