Search for dissertations about: "log-linear models"

Showing result 1 - 5 of 6 swedish dissertations containing the words log-linear models.

2. 1. Extensions of the kernel method of test score equating

   Author : Gabriel Wallin; Marie Wiberg; Jenny Häggström; Anton A. Béguin; Umeå universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; Test equating; Nonequivalent groups; Standard error of equating; bandwidth selection; log-linear models; item response theory; Statistics; statistik;

   Abstract : This thesis makes contributions within the area of test score equating and specifically kernel equating. The first paper of this thesis studies the estimation of the test score distributions needed in kernel equating. READ MORE

4. 2. Bayesian inference in probabilistic graphical models

   Author : Felix Leopoldo Rios; Tatjana Pavlenko; Alun Thomas; KTH; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; Graphical models; Bayesian inference; predictive classification; decomposable graphs; Tillämpad matematik och beräkningsmatematik; Applied and Computational Mathematics;

   Abstract : This thesis consists of four papers studying structure learning and Bayesian inference in probabilistic graphical models for both undirected and directed acyclic graphs (DAGs).Paper A presents a novel algorithm, called the Christmas tree algorithm (CTA), that incrementally construct junction trees for decomposable graphs by adding one node at a time to the underlying graph. READ MORE

5. 3. Using Markov models and a stochastic Lipschitz condition for genetic analyses

   Author : Carl Nettelblad; Sverker Holmgren; José M. Álvarez-Castro; Uppsala universitet; []
   Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Beräkningsvetenskap; Scientific Computing;

   Abstract : A proper understanding of biological processes requires an understanding of genetics and evolutionary mechanisms. The vast amounts of genetical information that can routinely be extracted with modern technology have so far not been accompanied by an equally extended understanding of the corresponding processes. READ MORE

6. 4. On ionising radiation and breast cancer risk

   Author : Anders Mattsson; Karolinska Institutet; Karolinska Institutet; []
   Keywords : ionising radiation; breast cancer induction; cancer induction; risk models; risk modification; pooled analysis; mammmographic screening; gained lost years of life;

   Abstract : Background: It is well known that exposure to ionising radiation increases the risk for breast cancer occurrence. However, better understanding of breast cancer risks in terms of dose-response relationships formulated according to radiobiological target theories, age-at-exposure patterns and temporal dependence are important for the understanding of the underlying biological mechanism of radiation carcinogenesis as well as for the concern about possible risks associated with the very low doses received from routine mammographic screening. READ MORE

7. 5. Statistical methods for twin and sibling designs

   Author : Johan Zetterqvist; Karolinska Institutet; Karolinska Institutet; []
   Keywords : ;

   Abstract : Twin and sibling studies are valuable in that they allow adjustment for potential confounding factors that are impossible or hard to measure. By measuring associations ‘within-cluster’ it is possible to adjust for many factors that are shared between individuals in the same cluster. READ MORE