published_or_final_version / Statistics and Actuarial Science / Doctoral / Doctor of Philosophy

No description available.

No description available.

by Wai-chung Lui. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1994. / Includes bibliographical references (leaves 76-82). / Chapter Chapter 1 --- Introduction --- p.1 / Chapter Chapter 2 --- Estimation of the model with one truncated continuous variable and one polytomous variable --- p.6 / Chapter §2.1 --- The model / Chapter § 2.2 --- Likelihood function of the model / Chapter § 2.3 --- Derivatives of F (θ） / Chapter § 2.4 --- Asymptotic properties of the model / Chapter Chapter 3 --- Estimation of the model with one truncated continuous variable and several polytomous variables --- p.22 / Chapter § 3.1 --- The model / Chapter § 3.2 --- Partition Maximum Likelihood (PML) estimation / Chapter § 3.3 --- Asymptotic properties of the PML estimates / Chapter Chapter 4 --- Optimization procedures and Simulation study --- p.43 / Chapter § 4.1 --- Optimization procedures / Chapter § 4.2 --- Simulation study / Chapter Chapter 5 --- Summary and Conclusion --- p.54 / Tables --- p.56 / References --- p.76

No description available.

<p>In this paper we aim to investigate volatility and correlation of sector</p><p>indexes of Nordic Market. More precisely we work with OMX Stockholm</p><p>Exchange Indexes, considering the Paper, the Energy and the Bank</p><p>sectors.</p><p>We use daily returns over the period from 5 January 2001 to 13 April</p><p>2007 and compute and forecast return volatility using the GARCH(1; 1)</p><p>model. We also calculate the correlation matrix of the indexes.</p><p>The GARCH(1; 1) model ¯t the empirical data well for all three sectors</p><p>and can therefore be used for volatility forecasts. Here, we have pre-</p><p>dicted the one-day-ahead forecasts and based on these data calculated</p><p>the correlation matrix. The results from these calculations show that</p><p>all three sectors are highly correlated. We obtained however the small-</p><p>est correlation between Paper and Energy which was surprising as the</p><p>Paper industry is very energy consuming. This result indicates other</p><p>relations between Paper and Energy.</p>

This thesis is dedicated to the development, implementation and application of a combination of Density Functional Theory and Dynamical Mean Field Theory. The resulting program is shown through several examples to be a powerful and flexible tool for calculating the electronic structure of strongly correlated materials. The main part of this work is focused on the development and implementation of three methods for solving the effective impurity model arising in the Dynamical Mean Field Theory: Hubbard-I approximation (HIA), Exact Diagonalization (ED), and Spin-Polarized T-matrix Fluctuation-exchange (SPTF). The Hubbard-I approximation is limited to systems where the hybridization between the 4f-orbitals and the rest of the material can be completely neglected, and can therefore not capture any Kondo physics. It has been used to study the atomic-like multiplet spectrum of the strongly localized 4f-electrons in the Lanthanide compounds YbInCu4, YbB12, Yb2Pd2Sn, YbPd2Sn, SmB6, SmSn3, and SmCo5. The calculated spectral properties are shown to be in excellent agreement with experimental direct and inverse photoemission data, clearly affirming the applicability of the Hubbard-I approximation for this class of systems if we are not focusing on Kondo physics. Full self-consistence in both self-energy and electron density is shown to be of key importance in the extraction of the magnetic properties of the hard permanent magnet SmCo5. The Exact Diagonalization solver is implemented as an extension of the Hubbard-I approximation. It takes into account a significant part of the hybridization between the correlated atom and the host through the use of a few effective bath orbitals. This approach has been applied to the long-standing problem of the electronic structure of NiO, CoO, FeO, and MnO. The resulting spectral densities are favorably compared to photoemission spectroscopy. Apart from predicting the correct spectral properties, the Exact Diagonalization solver also provides full access to the many-body density operator. This feature is used to make an in-depth investigation of the correlations in the electronic structure, and two measures of the quantum entanglement of the many-body ground-states are presented. It is shown that CoO possesses the most intricate entanglement properties, due to a competition between crystal field effects and Coulomb interaction, and such a mechanism likely carries over to several classes of correlated electron systems. The Exact Diagonalization solver has also been applied to the prototypical dilute magnetic semiconductor Mn doped GaAs, a material of great importance in the study of future spintronics applications. The problem of Fe impurities in Cs has been used to study the dependence of the spectral properties on the local environment. Finally, the Spin-polarized T-matrix Fluctuation-exchange solver has been implemented and applied to more delocalized electron systems where the effective impurity problem can be solved as a perturbation with respect to the strength of the local Coulomb interaction. This approach has been used to study the magnetic and spectral properties of the late transition metals, Fe, Co and Ni, and NiS.

One of the most important considerations in winning a competitive bid is the determination of an optimum strategy developed by predicting the competitor's most probable actions. There may be some common factors for different contractors in establishing their bid prices, such as references for cost estimating, construction materials, site conditions, or labor prices. Those dependencies from past bids can be used to improve the strategy to predict future bids. By identifying the interrelationships between bidders with statistical correlations, this study provides an overview of how correlations among bidders influence the bidders winning probability. With data available for over 7,000 Michigan Department of Transportation highway projects that can be used to calculate correlations between the different contractors, a Monte Carlo simulation is used to generate correlated random variables and the probability of winning from the results of the simulation. The primary focus of this paper outlines the use of conditional probability for predicting the probability of winning to establish a contractor's strategy for remaining bids with their estimated bid price and known information about competitors from past data. If a contractor estimated his/her bid price to be lower than his/her average bid, a higher probability of winning would be achieved with competitors who have a low correlation with the contractor. Conversely, the lower probability of winning decreases as the contractor bid with highly correlated contractors when their bid price is estimated to be higher than the average bid.

In this paper we aim to investigate volatility and correlation of sector indexes of Nordic Market. More precisely we work with OMX Stockholm Exchange Indexes, considering the Paper, the Energy and the Bank sectors. We use daily returns over the period from 5 January 2001 to 13 April 2007 and compute and forecast return volatility using the GARCH(1; 1) model. We also calculate the correlation matrix of the indexes. The GARCH(1; 1) model ¯t the empirical data well for all three sectors and can therefore be used for volatility forecasts. Here, we have pre- dicted the one-day-ahead forecasts and based on these data calculated the correlation matrix. The results from these calculations show that all three sectors are highly correlated. We obtained however the small- est correlation between Paper and Energy which was surprising as the Paper industry is very energy consuming. This result indicates other relations between Paper and Energy.

Thesis (Ph. D.)--Ohio State University, 2004. / Title from first page of PDF file. Document formatted into pages; contains xiii, 116 p.; also includes graphics. Includes abstract and vita. Advisor: H.N. Nagaraja, Dept. of Statistics. Includes bibliographical references (p. 113-116).