Sökning: "statistics of extreme values"

Visar resultat 1 - 5 av 18 avhandlingar innehållade orden statistics of extreme values.

1. 1. Some Contributions to Description and Validation of the Extreme Value Distribution

   Författare :MirNabi PirouziFard; Statistiska institutionen; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; weighted least squares estimator.; probability plot; power of tests; extreme value distribution; variances and covariances; goodness-of-fit tests; order statistics; Approximations of means;

   Sammanfattning : This thesis focuses on the validation and description of the Gumbel distribution. Since this is a scale and location parameter distribution, the generalized least squares regression of the order statistics on the expected values can be used, without the necessity of iteration, to obtain the best linear unbiased estimates of the parameters. LÄS MER

3. 2. Survey estimation for highly skewed data

   Författare :Forough Karlberg; Chris Skinner; Stockholms universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Extreme values; skewed populations; model-based inference; superpopulation; lognormal distribution; statistik; Statistics;

   Sammanfattning : Estimation of the population total of a highly skewed survey variable from a small sample is problematic if straightforward methods are used since (i) when there are no extreme values in the sample, too small estimates will be obtained (ii) if extreme values are sampled, the estimates will become grotesquely large. Traditional methods for outlier treatment will usually compensate for outliers in the sample, thereby avoiding (ii), whereas the small negative bias of (i) will persist. LÄS MER

4. 3. Estimation of Nonlinear Latent Variable and Mixture Models

   Författare :Johan Vegelius; Shaobo Jin; Fan Yang-Wallentin; Melanie Wall; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; structural equation modeling; semiparametric; EM algorithm; adaptive Gauss-Hermite quadrature approximation; Laplace approximation; zero inflation; Statistics; Statistik;

   Sammanfattning : In this thesis methods are developed for estimation of latent variable models. In particular nonlinear structural equation models are estimated in the presence of ordinal data and mixture models for count data. LÄS MER

5. 4. Large and rare : An extreme values approach to estimating the distribution of large defects in high-performance steels

   Författare :Jens Ekengren; Jens Bergström; Christer Burman; Thomas Svensson; Karlstads universitet; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Non-metallic inclusions; Tool steel; Extreme value statistics; Distribution of defects; Generalized extreme values; Materialteknik; Materials Engineering;

   Sammanfattning : The presence of different types of defects is an important reality for manufacturers and users of engineering materials. Generally, the defects are either considered to be the unwanted products of impurities in the raw materials or to have been introduced during the manufacturing process. LÄS MER

7. 5. Extreme Value Analysis of Huge Datasets: Tail Estimation Methods in High-Throughput Screening and Bioinformatics

   Författare :Dmitrii Zholud; Göteborgs universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Extreme Value Statistics; High-Throughput Screening; HTS; Bioinformatics; analysis of huge datasets; quality control; correction of theoretical p-values; comparison of pre-processing methods; SmartTail; estimation of False Discovery Rates; test power; distribution tail; high level excursions; quantile estimation; multiple testing; Student t−test; Welch statistic; small sample sizes; F−test; Wiener process; Gaussian random walk; Shepp statistic; limit theorems; exotic options.; estimation of False Discovery Rates;

   Sammanfattning : This thesis presents results in Extreme Value Theory with applications to High-Throughput Screening and Bioinformatics. The methods described here, however, are applicable to statistical analysis of huge datasets in general. The main results are covered in four papers. LÄS MER