In this paper the relation between managerial ownership and conservatism is examined. Managerial ownership decreases agency problems caused by the separation of ownership and control. Managerial ownership increases the time horizon of managers and decreases expropriating behaviour. Conservatism is hypothesized to have the same effect on managers due to the asymmetric timeliness of earnings. This suggest that in firms with lower managerial ownership a demand for conservatism arises to substitute for the alignment function of managerial ownership. This paper test this with two approaches. The first replicates the methodology of previous literature. The findings provide no evidence for substitution between managerial ownership and conservatism. Because the estimators of the first methodology are biased a second method is used applying fixed effects. Consistent with the first approach no supporting evidence is found. However, it finds that firms in the sample have conservative accounting. The main implication of this paper is that rewarding managers with shares is not decreasing their conservative behaviour.

The extension of Conditional Random Fields (CRF) from discrete states to continuous states will help remove the limitation of the number of states and allow new applications for CRF. In this work, our attempts to obtain a correct procedure to train continuous state conditional random fields through maximum likelihood are presented. By deducing the equations governing the extension of the CRF to continuous states it was possible to merge with the Particle Filter (PF) concept to obtain a formulation governing the training of continuous states CRFs by using particle filters. The results obtained indicated that this process is unsuitable because of the low convergence of the PF integration rate in the needed integrations replacing the summation in CRFs. So a change in concept to an adaptive integration scheme was made. Based on an extension of the Binary Space Partition (BSP) algorithm an adaptive integration process was devised with the aim of producing a more precise integration while retaining a less costly function evaluation than PF. This allowed us to train continuous states conditional random fields with some success. To verify the possibility of increasing the dimension of the states as a vector of continuous states a scalable version was also used to briefly assess its fitness in two-dimensions with quadtrees. This is an asymmetric two-dimensional space partition scheme. In order to increase the knowledge of the problem it would be interesting to have further information of the relevant features. A feature selection embedded method was used based on the lasso regulariser with the intention of pinpointing the most relevant feature functions indicating the relevant features.

Background: There are a plethora of potential statistical designs which can be used to evaluate efficacy of a novel cancer treatment in the phase II clinical trial setting. Unfortunately, there is no consensus as to which design one should prefer, nor even which definition of efficacy should be used and the primary endpoint conclusion can vary depending on which design is chosen. It would be useful if an all-encompassing methodology was possible which could evaluate all the different designs simultaneously and allow investigators an understanding of the trial results under the varying scenarios. Methods: Finite Markov chain imbedding is a method which can be used in the setting of phase II oncology clinical trials but never previously evaluated in this scenario. Simple variations to the transition matrix or end-state probability definitions can be performed which allow for evaluation of multiple designs and endpoints for a single trial. A computer program is written in R which allows for computation of p-values and conditional power, two common statistical measures used for evaluation of trial results. A simulation study is performed on data arising from an actual phase II clinical trial performed recently in which the study conclusion regarding the efficacy of the potential treatment was debatable. Results: Finite Markov chain imbedding is shown to be useful for evaluating phase II oncology clinical trial results. The R code written for evaluating the simulation study is demonstrated to be fast and useful for investigating different trial designs. Further detail regarding the clinical trial results are presented, including the potential prolongation of stable disease of the treatment, which is a potentially useful marker of efficacy for this cytostatic agent. Conclusions: This novel methodology may prove to be an useful investigative technique for the evaluation of phase II oncology clinical trial data. Future studies which have disputable conclusions might become less controversial with the aid of finite Markov chain imbedding and the possible multiple evaluations which is now viable. Better understanding of activity for a given treatment might expedite the drug development process or help distinguish active from inactive treatments

The primary aim of this thesis is the elucidation of covariate effects on the dependence structure of random variables in bivariate or multivariate models. We develop a unified approach via a conditional copula model in which the copula is parametric and its parameter varies as the covariate. We propose a nonparametric procedure based on local likelihood to estimate the functional relationship between the copula parameter and the covariate, derive the asymptotic properties of the proposed estimator and outline the construction of pointwise confidence intervals. We also contribute a novel conditional copula selection method based on cross-validated prediction errors and a generalized likelihood ratio-type test to determine if the copula parameter varies significantly. We derive the asymptotic null distribution of the formal test. Using subsets of the Matched Multiple Birth and Framingham Heart Study datasets, we demonstrate the performance of these procedures via analyses of gestational age-specific twin birth weights and the impact of change in body mass index on the dependence between two consequent pulse pressures taken from the same subject.

The thesis evaluates the benefit of allowing for long memory volatility dynamics in forecasts of the variance-covariance matrix for asset allocation. First, I compare the forecast performance of multivariate long memory conditional volatility models (the long memory EWMA, long memory EWMA-DCC, FIGARCH-DCC and Component GARCH-DCC models) with that of short memory conditional volatility models (the short memory EWMA and GARCH-DCC models), using the asset allocation framework of Engle and Colacito (2006). The research reports two main findings. First, for longer horizon forecasts, long memory volatility models generally produce forecasts of the covariance matrix that are statistically more accurate and informative, and economically more useful than those produced by short memory volatility models. Second, the two parsimonious long memory EWMA models outperform the other models – both short memory and long memory – in a majority of cases across all forecast horizons. These results apply to both low and high dimensional covariance matrices with both low and high correlation assets, and are robust to the choice of estimation window. The research then evaluates the application of multivariate long memory conditional volatility models in dynamic asset allocation, applying the volatility timing procedure of Fleming et al. (2001). The research consistently identifies the economic gains from incorporating long memory volatility dynamics in investment decisions. Investors are willing to pay to switch from the static to the dynamic strategies, and especially from the short memory volatility timing to the long memory volatility timing strategies across both short and long investment horizons. Among the long memory conditional volatility models, the two parsimonious long memory EWMA models, again, generally produce the most superior portfolios. When transaction costs are taken into account, the gains from the daily rebalanced dynamic portfolios deteriorate; however, it is still worth implementing the dynamic strategies at lower rebalancing frequencies. The results are robust to estimation error in expected returns, the choice of risk aversion coefficients and the use of a long-only constraint. To control for estimation error in forecasts of the long memory high dimensional covariance matrix, the research develops a dynamic long memory factor (the Orthogonal Factor Long Memory, or OFLM) model by embedding the univariate long memory EWMA model of Zumbach (2006) into an orthogonal factor structure. The factor-structured OFLM model is evaluated against the six above multivariate conditional volatility models in terms of forecast performance and economic benefits. The results suggest that the OFLM model generally produces impressive forecasts over both short and long forecast horizons. In the volatility timing framework, portfolios constructed with the OFLM model consistently dominate the static and other dynamic volatility timing portfolios in all rebalancing frequencies. Particularly, the outperformance of the factor-structured OFLM model to the fully estimated LM-EWMA model confirms the advantage of the factor structure in reducing estimation error. The factor structure also significantly reduces transaction costs, making the dynamic strategies more feasible in practice. The dynamic factor long memory volatility model also consistently produces more superior portfolios than those produced by the traditional unconditional factor and the dynamic factor short memory volatility models.

This thesis introduces a new quantity called loop number, and shows the conditions in which loop numbers become knot invariants. For a given knot diagram D, one can traverse the knot diagram and count the number of loops created by the traversal. The number of loops recorded depends on the starting point in the diagram D and on the traversal direction. Looking at the minimum or maximum number of loops over all starting points and directions, one can define two positive integers as loop numbers of the diagram D. In this thesis, the conditions under which these loop numbers become knot invariants are identified. In particular, the thesis answers the question when these numbers are invariant under flypes in the diagram D.

The conditional control of equivalence has received much attention in the analysis of verbal behavior. While previous research identified conditional control of relational responding and conditional control of equivalence class formation, this study investigated the possibility of conditional control of members of an equivalence class. Following baseline conditional discrimination training and equivalence testing, subjects were taught to select a particular member in the presence of a Green background screen and another member in the presence of a Red background screen.

Individuals with autism often have deficient intraverbal repertoires. Previous research has found success in using a blocked trials procedure to facilitate discrimination training. A previous study (unpublished) from our laboratory extended this procedure to intraverbal training. The current study continued this line of research by exploring the outcomes of probing the criterion performance more frequently. Three children with autism, ages 7-13, participated. Eight question pairs were taught. One question was presented repeatedly until a specified number of consecutive correct responses occurred, then the other question was presented. Contingent on specific mastery criteria, the trial blocks were faded into smaller blocks until the questions were presented in quasi-random order. Between each step, a criterion probe was conducted to determine if further steps were necessary. The procedure has been successful for two of the three participants. Criterion probe performance showed that not all teaching steps were needed every time. The procedure may have facilitated acquisition over time, because the number of trials to mastery generally decreased over successive targets.

We investigate the interdependence among three CEE stock markets and be- tween CEEs vis-à-vis euro area, using daily data from 2001-2011. Initially, we estimate bivariate ADCC models. Then, OLS regressions are employed to understand the evolution of correlations in time and during the recent financial crises. Finally, we examine the relationship between correlations and volatilities using the simple OLS model and the rolling stepwise regression methodology. Our results indicate that 3 out of 4 series exhibit asymmetries in conditional variances, while only 1 pair out of 6 exhibit asymmetries in correlations. We found that correlations are increased over time and during the recent financial crises for both pairs (CEEs-CEEs and CEEs-eurozone). However, the highest increase is observed for CEEs-eurozone. Mainly, we found a positive rela- tionship between correlations and volatilities, even though this relationship is niether constant in time nor strictly positive or negative during all the sample period, but rather time-varying with periods of being higher or lower than zero.

In this diploma thesis we explain the main principles and properties of bootstrap methods, that can be used to conduct the statistical inference in linear and nonlinear financial time series. We will introduce basic ideas of bootstrap methods for the case when observations can be considered as independent random variables, and afterwards we will describe more advanced methods, that can be successfully used when we are dealing with time series. Thesis deals with both parametric bootstrap methods, that we can use when the underlying parametric model of observations is available, as well as with nonparametric bootstrap methods that are used when more general nonparametric model of time series data is considered. The main objective is to compare particular bootstrap methods and show the usage of these methods on real world data. There is also a basic time series theory included in the work. 1