No description available.

No description available.

Now that we’ve studied the sum-of-products form of Boolean expressions, it’s time to take a look at the product-of-sums. This form uses logical OR’s to generate zeros which are passed to the output through an AND gate.

For the exponential response η_u = α + βe^γZ_u (u = 1,2,…,N) where α and β lie on the real line (-∞,∞), and γ is a positive integer; the designs are given which minimize the bias due to the inherent inability of the approximation function ŷ_u = Σ_j=0<sup>d</sub>b_je^jZ_u to fit such a model. Transformation to η_u = α + βx_u^γ and ŷ_u = Σ_j=0<sup>d</sub>b_jx_u^j facilitates the solution for minimum bias designs. The requirements for minimum bias designs follow along lines similar to those given by Box and Draper (J. Amer. Stat. Assoc., 54, 1959, p. 622). The minimum bias designs are obtained for specific values of N with a maximum protection level, γ_d*(N), for the parameter γ and an approximation function of degree d. These designs obtained possess several degrees of freedom in the choice of the design levels of the x_u or the Z_uu , which may be used to satisfy additional design requirements. It is shown that for a given N, the same designs which minimize bias for approximation functions of degree one also minimize bias for general degree d, with a decrease in γ_d*(N) as d increases. In fact γ_d*(N) = γ₁*(N) - d + 1, but with the decrease in γ_d*(N) is a compensating decrease in the actual level of the minimum bias. Furthermore, γ_d*(N) increases monotonically with N, thereby allowing the maximum protection level on 1 to be increased as desired by increasing N. In the course of obtaining solutions, some interesting techniques are developed for determining the nature of the roots of a polynomial equation which has several known coefficients and several variable coefficients. / Ph. D.

No description available.

Cette thèse concerne quelques problèmes liés à la répartition des entiers sans facteur carré dansles progressions arithmétiques. Ces problèmes s’expriment en termes de majorations du terme d’erreurassocié à cette répartition.Les premier, deuxième et quatrième chapitres sont concentrés sur l’étude statistique des termesd’erreur quand on fait varier la progression arithmétique modulo q. En particulier on obtient une formuleasymptotique pour la variance et des majorations non triviales pour les moments d’ordre supérieur. Onfait appel à plusieurs techniques de théorie analytique des nombres comme les méthodes de crible et lessommes d’exponentielles, notamment une majoration récente pour les sommes d’exponentielles courtesdue à Bourgain dans le deuxième chapitre.Dans le troisième chapitre on s’intéresse à estimer le terme d’erreur pour une progression fixée. Onaméliore un résultat de Hooley de 1975 dans deux directions différentes. On utilise ici des majorationsrécentes de sommes d’exponentielles courtes de Bourgain-Garaev et de sommes d’exponentielles torduespar la fonction de Möbius dues à Bourgain et Fouvry-Kowalski-Michel. / This thesis concerns a few problems linked with the distribution of squarefree integers in arithmeticprogressions. Such problems are usually phrased in terms of upper bounds for the error term relatedto this distribution.The first, second and fourth chapter focus on the satistical study of the error terms as the progres-sions varies modulo q. In particular we obtain an asymptotic formula for the variance and non-trivialupper bounds for the higher moments. We make use of many technics from analytic number theorysuch as sieve methods and exponential sums. In particular, in the second chapter we make use of arecent upper bound for short exponential sums by Bourgain.In the third chapter we give estimates for the error term for a fixed arithmetic progression. Weimprove on a result of Hooley from 1975 in two different directions. Here we use recent upper boundsfor short exponential sums by Bourgain-Garaev and exponential sums twisted by the Möbius functionby Bourgain et Fouvry-Kowalski-Michel.

No description available.

In this thesis, two methods for assessing the functional form of covariates in the Cox proportional hazards model are evaluated. The methods include one graphical check based on martingale residuals and one graphical check, together with a Kolmogorov-type supremum test, based on cumulative sums of martingale residuals. The methods are evaluated in a simulation study under five different covariate misspecifications with varying sample sizes and censoring degrees. The results from both methods indicate that the type of covariate misspecification, sample size and censoring degree affect the ability to detect and identify the misspecification. The procedure based on smoothed scatterplots of martingale residuals reveals difficulties with assessing whether the behaviour of the smoothed curve in the plot is an indication of a misspecification or a phenomenon that can occur in a correctly specified model. The graphical check together with the test procedure based on cumulative sums of martingale residuals is shown to successfully detect and identify three out of five covariate misspecifications for large sample sizes. For small sample sizes, especially combined with a high censoring degree, the power of the supremum test is low for all covariate misspecifications.

No description available.

Neste trabalho fazemos um estudo do conceito de soma torcida de F-espaços. Apresentamos algumas propriedades e simplificações na construção de somas torcidas de F-espaços localmente limitados. Em particular, estudamos uma condição suficiente para que uma soma torcida de espaços de Banach seja um espaço de Banach. Finalmente aplicamos esses conceitos para definir o espaço construído por N. J. Kalton, que é um exemplo de um espaço de Banach não isomorfo ao conjugado complexo. Este espaço X de Kalton corresponde a uma soma torcida de espaços de Hilbert, isto é, X possui um subespaço fechado E tal que E e X/E são isomorfos a espaços de Hilbert. / In this work we study the concept of twisted sum of F-spaces. We also study some properties and simplifications in the construction of twisted sums of locally bounded F-spaces. In particular, we study a sufficient condition for a twisted sum of Banach spaces to be a Banach space. Finally we apply these concepts to define the space constructed by N. J. Kalton, which is an example of a Banach space not isomorphic to its complex conjugate. The Kalton space X is a twisted sum of Hilbert spaces, i.e. X has a closed subspace E such that E and X/E are isomorphic to Hilbert spaces.