Sökning: "Matrix Normal Distribution"
Visar resultat 1 - 5 av 9 uppsatser innehållade orden Matrix Normal Distribution.
1. Mäns kompensatoriska beteende i hushållsarbetet : En kvalitativ studie gjord på män med familj som i sitt arbete veckopendlar
Kandidat-uppsats, Mittuniversitetet/Institutionen för humaniora och samhällsvetenskapSammanfattning : The study is a qualitative study conducted via telephone interviews where the material has been transcribed and processed with qualitative text analysis and presented under themes and analyzed based on Butler's (2005) theory of the heterosexual matrix, Connell & Pearse (2017), social embodiment and gender domain and Gorman-Murray (2008) masculinity and previous research. The topic of gender with the home as the focus is a current topic and in this study we interviewed eight men between 28-40 years who work in a craft profession far from home, i. LÄS MER
2. Testing Structure of Covariance Matrix under High-dimensional Regime
Master-uppsats, Linköpings universitet/Statistik och maskininlärningSammanfattning : Statisticians are interested in testing the structure of covariance matrices, especially under the high-dimensional scenario in which the dimensionality of data matrices exceeds the sample size. Many test statistics have been introduced to test whether the covariance matrix is equal to identity structure (), sphericity structure () or diagonal structure (). LÄS MER
3. Biomarkörer i ledvätska och serum som metod för att diagnostisera osteoartrit hos häst
Kandidat-uppsats, SLU/Dept. of Biomedical Sciences and Veterinary Public HealthSammanfattning : Synovialleden är den vanligaste ledtypen i hästens extremiteter och drabbas ofta av osteoartrit (OA). Leden består av flera delar som samverkar med varandra, både i friska och sjuka leder, därför bör den betraktas som ett organ. LÄS MER
4. A Mixed Frequency Steady-State Bayesian Vector Autoregression: Forecasting the Macroeconomy
Master-uppsats, Uppsala universitet/Statistiska institutionenSammanfattning : This thesis suggests a Bayesian vector autoregressive (VAR) model which allows for explicit parametrization of the unconditional mean for data measured at different frequencies, without the need to aggregate data to the lowest common frequency. Using a normal prior for the steady-state and a normal-inverse Wishart prior for the dynamics and error covariance, a Gibbs sampler is proposed to sample the posterior distribution. LÄS MER
5. Explicit Estimators for a Banded Covariance Matrix in a Multivariate Normal Distribution
Kandidat-uppsats, Linköpings universitet/Matematisk statistik; Linköpings universitet/Tekniska högskolanSammanfattning : The problem of estimating mean and covariances of a multivariate normal distributedrandom vector has been studied in many forms. This thesis focuses on the estimatorsproposed in [15] for a banded covariance structure with m-dependence. LÄS MER