Sökning: "linear regression"

Visar resultat 6 - 10 av 492 avhandlingar innehållade orden linear regression.

  1. 6. Optimal Segmentation of Linear Regression Parameters

    Författare :Fredrik Gustafsson; Linköpings universitet; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY;

    Sammanfattning : The problem of detecting multiple changes in the dynamical properties of a measured signal, which we call segmentation, is studied. A Bayesian model-based approach is used. The signal is supposed to be described by a linear regression. The posterior distribution for the change instants is first derived for a quite general signal model. LÄS MER

  3. 7. A regression approach for assessment of building energy performance

    Författare :Jimmy Vesterberg; Thomas Olofsson; Mohsen Soleimani-Mohseni; Björn Reidar Sörensen; Sofia Lidelöw; Umeå universitet; []
    Nyckelord :building energy simulation; measurements; regression; calibration parameters;

    Sammanfattning : Reliable evaluation methods is needed to ensure that investments in energy conservation measures (ECMs) and the construction of new energy efficient buildings lives up to the promised and expected performance.This thesis presents and evaluates a regression method for estimation of influential building parameters: transmission losses above ground (including air leakage), ground heat loss, and overall heat loss coefficient. LÄS MER

  4. 8. Bayesian Sequential Inference for Dynamic Regression Models

    Författare :Parfait Munezero; Mattias Villani; Helga Wagner; Stockholms universitet; []
    Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Bayesian sequential inference; Dynamic regression models; Particle filter; Online prediction; Particle smoothing; Linear Bayes; Statistics; statistik;

    Sammanfattning : Many processes evolve over time and statistical models need to be adaptive to change. This thesis proposes flexible models and statistical methods for inference about a data generating process that varies over time. The models considered are quite general dynamic predictive models with parameters linked to a set of covariates via link functions. LÄS MER

  5. 9. Latent variable based computational methods for applications in life sciences : Analysis and integration of omics data sets

    Författare :Max Bylesjö; Johan Trygg; Tormod Naes; Umeå universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Chemometrics; orthogonal projections to latent structures; OPLS; O2PLS; K-OPLS; kernel-based; non-linear; regression; classification; Populus; Chemistry; Kemi;

    Sammanfattning : With the increasing availability of high-throughput systems for parallel monitoring of multiple variables, e.g. levels of large numbers of transcripts in functional genomics experiments, massive amounts of data are being collected even from single experiments. LÄS MER

  7. 10. Tests of random effects in linear and non-linear models

    Författare :Erling Häggström Lundevaller; Umeå universitet; []
    Nyckelord :Random effects; score test; NLS; heteroskedasticity; measurement error; Poisson regression; trip frequencies; Statistics; statistik;

    Sammanfattning : .... LÄS MER