{"id":640,"date":"2017-09-28T06:57:07","date_gmt":"2017-09-28T06:57:07","guid":{"rendered":"http:\/\/jsr.isrt.ac.bd\/?post_type=article&p=640"},"modified":"2017-09-28T06:57:36","modified_gmt":"2017-09-28T06:57:36","slug":"short-review-multivariate-t-distribution","status":"publish","type":"article","link":"http:\/\/jsr.isrt.ac.bd\/article\/short-review-multivariate-t-distribution\/","title":{"rendered":"A short review of multivariate t-distribution"},"content":{"rendered":"
This paper reviews most important properties of a location-scale multivariate
\n-distribution. A conditional representation of the distribution is exploited to
\noutline moments, characteristic function, marginal and conditional distributions,
\ndistribution of linear combinations and quadratic forms. Stochastic representation
\nis also used to determine the covariance matrix of the distribution. It also
\nmakes an attempt to justify an uncorrelated – model and overviews distribution
\nof the sum of products matrix and correlation matrix. Estimation strategies for
\nparameters of the model is briefly discussed. Finally the recent trend of linear
\nregression with the uncorrelated – model is discussed.<\/p>\n