Thesis (Ph. D.)--York University, 2001. Graduate Programme in Economics. / Typescript. Includes bibliographical references (leaves 116-121). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://wwwlib.umi.com/cr/yorku/fullcit?pNQ67896.

The development of a child can be monitored by studying the changes in physical appearance or the development of capabilities e.g. walking and talking. But is it possible to find a quantitative measure for brain development? The aim of this thesis work is to investigate that possibility using quantitative magnetic resonance imaging (qMRI) images by answering the following questions: Can brain development be determined using qMRI? If so, what properties of the brain can be used? Can the age of a child be automatically detected with an algorithm? If so, how can this algorithm function? With what accuracy? Previous studies have shown that it is possible to detect properties in the brain changing with age, based on MRI images. These properties have e.g. been changes in T1 and T2 relaxation time, i.e. properties in water signal behavior that can be measured using multiple MR acquisitions. In the literature this was linked to a rapid myelination process that occurs after birth. Furthermore the organization and growth of the brain is a property that can be measured and monitored. This thesis have investigated several different properties in the brain based on qMRI images in order to identify those who have a strong correlation with age in the range 0-20 years. The properties that were found to have a high correlation were: Position of the first histogram peak in T1 weighted qMRI images, Fraction of white matter in the brain, Mean pixel value of PD weighted qMRI images, Volume of white matter in the brain, Curves on the form f(x) = ae^(-bx) +c are fitted to the data sets and confidence intervals are calculated to frame the statistical insecurity of the curve. The mean error in percent for the different properties can be seen in the list below: Property, Mean error [%] 0-20 years, Mean error [%] 0-3 years Peak position: 53.84, 98.17 Fraction of WM: 118.97, 71.67 Mean pixel value: 200.89, 126.28 Volume of WM: 241.72, 72.58 The conclusions drawn based on the presented results are that there are properties in the brain that correlates well to aging, but the error is too large for making a valid prediction of age over the entire range of 0-20 years. When decreasing the age range to 0-3 years the mean error becomes smaller, but it is still too large. More data is needed to evaluate and improve this result.

Existing methods for image-based location estimation generally attempt to recognize every photo independently, and their resulting reliance on strong visual feature matches makes them most suited for distinctive landmark scenes. We observe that when touring a city, people tend to follow common travel patterns---for example, a stroll down Wall Street might be followed by a ferry ride, then a visit to the Statue of Liberty or Ellis Island museum. We propose an approach that learns these trends directly from online image data, and then leverages them within a Hidden Markov Model to robustly estimate locations for novel sequences of tourist photos. We further devise a set-to-set matching-based likelihood that treats each ``burst" of photos from the same camera as a single observation, thereby better accommodating images that may not contain particularly distinctive scenes. Our experiments with two large datasets of major tourist cities clearly demonstrate the approach's advantages over traditional methods that recognize each photo individually, as well as a naive HMM baseline that lacks the proposed burst-based observation model. / text

What motivates mergers in banking? The data show that merger activity is concentrated among very large banks. A large literature on the banking structure has studied this question by estimating cost functions and has provided mixed evidence. A crucial assumption is the exogeneity of input prices.If this assumption fails, result may be biased. This paper adopts the production function method proposed by Levinsohn and Petrin (2003) to separate the impact of productivity from scale economies in banking. To avoid this bias, I use recovery rates of non-performing loans, charge off rates, and cash holdings as proxies for productivity. The proxy method illustrates that the industry operates with significant diseconomies of scale, while the OLS method generates opposite results. Therefore, this finding supports the view that improvements in productivity cause mergers, which is also consistent with data. Finally, I introduce the Quantile Proxy Method to capture the impacts of both input endogeneity and size heterogeneity. This method reveals that medium size banks have largest diseconomies of scale, while top 5% experience somewhat extensive economies of scale. This result sheds light on the fact why many mergers occur among large banks: large parties involved in a consolidation benefit from both productivity improvements and scale economies. / text

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

published_or_final_version / Statistics and Actuarial Science / Master / Master of Philosophy

In longitudinal and spatio-temporal data analysis, repeated measurements from a subject can be either regional- or temporal-dependent. The correct specification of the within-subject covariance matrix cultivates an efficient estimation for mean regression coefficients. In this thesis, robust estimation for the mean and covariance jointly for the regression model of longitudinal data within the framework of generalized estimating equations (GEE) is developed. The proposed approach integrates the robust method and joint mean-covariance regression modeling. Robust generalized estimating equations using bounded scores and leverage-based weights are employed for the mean and covariance to achieve robustness against outliers. The resulting estimators are shown to be consistent and asymptotically normally distributed. Robust variable selection method in a joint mean and covariance model is considered, by proposing a set of penalized robust generalized estimating equations to estimate simultaneously the mean regression coefficients, the generalized autoregressive coefficients and innovation variances introduced by the modified Cholesky decomposition. The set of estimating equations select important covariate variables in both mean and covariance models together with the estimating procedure. Under some regularity conditions, the oracle property of the proposed robust variable selection method is developed. For these two robust joint mean and covariance models, simulation studies and a hormone data set analysis are carried out to assess and illustrate the small sample performance, which show that the proposed methods perform favorably by combining the robustifying and penalized estimating techniques together in the joint mean and covariance model. Capturing dynamic change of time-varying correlation structure is both interesting and scientifically important in spatio-temporal data analysis. The time-varying empirical estimator of the spatial correlation matrix is approximated by groups of selected basis matrices which represent substructures of the correlation matrix. After projecting the correlation structure matrix onto the space spanned by basis matrices, varying-coefficient model selection and estimation for signals associated with relevant basis matrices are incorporated. The unique feature of the proposed model and estimation is that time-dependent local region signals can be detected by the proposed penalized objective function. In theory, model selection consistency on detecting local signals is provided. The proposed method is illustrated through simulation studies and a functional magnetic resonance imaging (fMRI) data set from an attention deficit hyperactivity disorder (ADHD) study. / published_or_final_version / Statistics and Actuarial Science / Doctoral / Doctor of Philosophy

The objective of this work is to develop a posteriori error estimates and adaptive strategies for the numerical solution to nonlinear systems of partial differential equations with uncertain data. Areas of application cover problems in fluid mechanics including a Bayesian model selection study of turbulence comparing different uncertainty models. Accounting for uncertainties in model parameters may significantly increase the computational time when simulating complex problems. The premise is that using error estimates and adaptively refining the solution process can reduce the cost of such simulations while preserving their accuracy within some tolerance. New insights for goal-oriented error estimation for deterministic nonlinear problems are first presented. Linearization of the adjoint problems and quantities of interest introduces higher-order terms in the error representation that are generally neglected. Their effects on goal-oriented adaptive strategies are investigated in detail here. Contributions on that subject include extensions of well-known theoretical results for linear problems to the nonlinear setting, computational studies in support of these results, and an extensive comparative study of goal-oriented adaptive schemes that do, and do not, include the higher-order terms. Approaches for goal-oriented error estimation for PDEs with uncertain coefficients have already been presented, but lack the capability of distinguishing between the different sources of error. A novel approach is proposed here, that decomposes the error estimate into contributions from the physical discretization and the uncertainty approximation. Theoretical bounds are proven and numerical examples are presented to verify that the approach identifies the predominant source of the error in a surrogate model. Adaptive strategies, that use this error decomposition and refine the approximation space accordingly, are designed and tested. All methodologies are demonstrated on benchmark flow problems: Stokes lid-driven cavity, 1D Burger’s equation, 2D incompressible flows at low Reynolds numbers. The procedure is also applied to an uncertainty quantification study of RANS turbulence models in channel flows. Adaptive surrogate models are constructed to make parameter uncertainty propagation more efficient. Using surrogate models and adaptivity in a Bayesian model selection procedure, it is shown that significant computational savings can be gained over the full RANS model while maintaining similar accuracy in the predictions. / text

Morphological characters have a long history of use in the estimation of phylogenetic trees. Datasets consisting of morphological characters are most often analyzed using the maximum parsimony criterion, which seeks to minimize the amount of character change across a phylogenetic tree. When combined with molecular data, characters are often analyzed using model-based methods, such as maximum likelihood or, more commonly, Bayesian estimation. The efficacy of likelihood and Bayesian methods using a common model for estimating topology from discrete morphological characters, the Mk model, is poorly-explored. In Chapter One, I explore the efficacy of Bayesian estimation of phylogeny, using the Mk model, under conditions that are commonly encountered in paleontological studies. Using simulated data, I describe the relative performances of parsimony and the Mk model under a range of realistic conditions that include common scenarios of missing data and rate heterogeneity. I further examine the use of the Mk model in Chapter Two. Like any model, the Mk model makes a number of assumptions. One is that transition between character states are symmetric (i.e., there is an equal probability of changing from state 0 to state 1 and from state 1 to state 0). Many characters, including alleged Dollo characters and extremely labile characters, may not fit this assumption. I tested methods for relaxing this assumption in a Bayesian context. Using empirical datasets, I performed model fitting to demonstrate cases in which modelling asymmetric transitions among characters is preferred. I used simulated datasets to demonstrate that choosing the best-fit model of transition state symmetry can improve model fit and phylogenetic estimation. In my final chapter, I looked at the use of partitions to model datasets more appropriately. Common in molecular studies, partitioning breaks up the dataset into pieces that evolve according to similar mechanisms. These pieces, called partitions, are then modeled separately. This practice has not been widely adopted in morphological studies. I extended the PartitionFinder software, which is used in molecular studies to score different possible partition schemes to find the one which best models the dataset. I used empirical datasets to demonstrate the effects of partitioning datasets on model likelihoods and on the phylogenetic trees estimated from those datasets. / text

Sammanfattning Syfte och frågeställningar: Syftet med denna studie var att a) undersöka om motionärer med Achilles tendinopati (AT) i mittportionen har nedsatt dorsalflexion i första metatarso-  falangealleden (MTP 1-leden) på affekterad sida jämfört med frisk b) undersöka om det finns sidoskillnader i naviculare position samt c) undersöka vilken metod - goniometermätning (GM) eller visuell estimation (VE) - som är att föredra vid mätning av dorsalflexionen i MTP 1-leden. Frågeställningarna var följande: Hur förhåller det sig med skillnaden för dorsalflexion i MTP 1-leden då affekterad sida jämförs med frisk hos motionärer med AT? Hur förhåller det sig med sidoskillnaden för fotvalvets höjd ? Hur förhåller det sig med sidoskillnaden för den vertikala rörligheten i mellanfoten? Hur förhåller det sig med mätvärdet för dorsalflexion i MTP 1-leden då affekterad sida jämförs med frisk vid användandet av respektive mätmetod (GM och VE)? Hur förhåller det sig med den samtidiga validiteten mellan VE och GM vid mätning av dorsalflexionen i MTP 1-leden? Metod: 28 patienter med unilateral AT (medelålder 39 år, symtomtid median 12 veckor), rekryterades konsekutivt. Patienterna diagnosticerades kliniskt, nedre extremitet screenades för rörelseinskränkningar i sagittalplanet, naviculares höjd (NH) mättes i två positioner och naviculare drop (ND) beräknades. MTP 1-leden fotograferades tre gånger i standardiserad mätposition och dorsalflexionen mättes med GM på fotografierna som randomiserats. Fotografierna med det högsta mätvärdet för respektive fots dorsalflexion i MTP 1-leden användes randomiserat för VE som utfördes med protokoll för standardisering. Resultat: Motionärer med AT uppvisade signifikant lägre medelvärde (p=0,015) för dorsalflexionen i MTP 1-leden på affekterad sida jämfört med frisk. Ingen signifikant sidoskillnad på medelvärdena för fotvalvets höjd (NH) eller på medelvärdena för vertikal rörlighet i mellanfoten (ND) förelåg. GM uppvisade signifikant högre medelvärde (p=0,0009) för dorsalflexion i MTP 1-leden jämfört med VE. Oavsett mätmetod (GM och VE), visade resultatet även ett signifikant (p= 0,047) högre medelvärde för dorsalflexionen i MTP 1-leden på frisk sida jämfört med affekterad. Pearson korrelation test visade r= 0,90 på frisk respektive r=0,86 på affekterad sida då metoderna VE och GM undersöktes för samvarians. Konklusion: Motionärer med unilateral AT har nedsatt dorsalflexion i MTP 1-leden på den affekterade sidan jämfört med friska. Inga sidoskillnader verkar finnas beträffande naviculare position. GM är att föredra framför VE vid klinisk mätning av dorsalflexion i MTP 1-leden, eftersom rörligheten underestimerades vid VE. / Abstract   Aim: The aim of this study was to a) investigate if recreational athletes diagnosed with midportion Achilles tendinopathy (AT) have restricted dorsiflexion in the 1st metatarsophalangeal (MTP) joint on affected side, compared to non-affected, b) investigate whether there are side side differences in naviculare position and also c) investigate which method - goniometric measurement (GM) or visual estimation (VE) - is preferable in measurement for dorsiflexion in the 1st MTP joint. The questions were: Is there a difference for dorsiflexion in the 1st MTP joint when comparing the affected side with the unaffected? Is there a side difference for the height of the medial longitudinal arch? Is there a side difference for the size of midtarsal vertical movement? Are there differences between the values of dorsiflexion in the 1st MTP joint using the respective method (GM and VE) when comparing the affected side to the unaffected? Does the method VE exhibit concurrent validity with the method GM in measuring dorsiflexion for the 1st MTP joint? Method: 28 patients with unilateral AT (mean age 39 years, weeks of symptoms median =12) were consecutively recruted. The patients were diagnosed clinically, the lower extremity was screened for restrictions in the sagittal plane, naviculare height (NH) was measured in two positions and navicular drop (ND) was calculated. The 1st MTP joint was photographed three times in a standardized position, and the dorsiflexion was measured by GM in the photos, which were randomized. The highest value measured for dorsiflexion in the 1st MTP joint for each foot was used for VE, and a protocol was used to standardize. Results: There was a significantly restricted dorsiflexion (p=0.015) in the 1st MTP joint on the affected side for recreational athletes with AT. There was no significance between the height of the longitudinal arch (NH) or the size of midtarsal vertical movement (ND) when comparing the affected side to the unaffected. Using GM there was a significantly higher mean (p= 0.0009) for dorsiflexion in the 1st MTP joint compared to VE. The mean was also significantly higher for dorsiflexion in the 1st MTP joint, using GM as well as VE, on the unaffected side, compared to the affected. When the methods VE and GM were examined for covariance, Pearson's correlation test showed r = 0.90 to the unaffected side and r = 0.86 to the affected side. Conclusions: Recreational athletes with unilateral AT have a restriction of dorsiflexion in the 1st MTP joint on the affected side compared to the unaffected. There were no side differences found between naviculare position. GM is to be chosen over VE for clinical measurements of dorsiflexion in the 1st MTP joint, since VE underestimated the range of motion.