<?xml version="1.0"?>
<rss version="2.0">
   <channel>
      <title>TMA4267 Linear Statistical Models Part 1: Multivariate random variables and the multivariate normal distribution by Mette Langaas</title>
      <link>https://padlet.com/mette_langaas/kvaua8nuc1rx</link>
      <description>What are the important results in this part of the course?</description>
      <language>en-us</language>
      <pubDate>2017-01-26 20:13:59 UTC</pubDate>
      <lastBuildDate>2026-02-26 13:03:47 UTC</lastBuildDate>
      <webMaster>hello@padlet.com</webMaster>
      <image>
         <url>https://padlet-assets.s3.amazonaws.com/icons/Thunder.png</url>
      </image>
      <item>
         <title>X is a p-dimensional vector of random variables with mean (p-dimensional vector) </title>
         <author>mette_langaas</author>
         <link>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149749975</link>
         <description><![CDATA[<var>\mu=\text{E}(X) </var><div>and covariance matrix (p times p symmetric and positive definite matrix) </div><var>\Sigma=\text{Cov}(X)=</var><div><br></div><var> \text{E}((X-\mu)(X-\mu)^T)=</var><div><br></div><var>\text{E}(XX^T)-\mu \mu^T.</var>]]></description>
         <enclosure url="" />
         <pubDate>2017-01-26 20:14:13 UTC</pubDate>
         <guid>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149749975</guid>
      </item>
      <item>
         <title>X is a p-dimensional random vector and C is k times p constant matrix. </title>
         <author>mette_langaas</author>
         <link>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149785649</link>
         <description><![CDATA[<var>\text{E}(CX)=C \text{E}(X) </var><div><br></div><var>\text{Cov}(CX)=C \text{Cov}(X)C^T</var>]]></description>
         <enclosure url="" />
         <pubDate>2017-01-27 00:05:43 UTC</pubDate>
         <guid>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149785649</guid>
      </item>
      <item>
         <title>V and W are random vectors. The covariance between V and W is</title>
         <author>mette_langaas</author>
         <link>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149785834</link>
         <description><![CDATA[<var>\text{Cov}(V,W)=</var><div><br></div><var>\text{E}((V-\text{E}(V))(W-\text{E}(W))^T) </var><div><br></div><var> = \text{E}(VW^T)-\text{E}(V)\text{E}(W^T)</var>]]></description>
         <enclosure url="" />
         <pubDate>2017-01-27 00:09:01 UTC</pubDate>
         <guid>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149785834</guid>
      </item>
      <item>
         <title>Multivariate momentgenerating function (MGF) for p-dimensional X:</title>
         <author>mette_langaas</author>
         <link>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149804316</link>
         <description><![CDATA[<var>M_X(t)=\text{E}(exp(t^TX))</var><div>where t is p-dimensional vector.</div>]]></description>
         <enclosure url="" />
         <pubDate>2017-01-27 06:53:37 UTC</pubDate>
         <guid>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149804316</guid>
      </item>
      <item>
         <title>Mean of quadratic form &quot;the trace formula&quot;</title>
         <author>mette_langaas</author>
         <link>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149804428</link>
         <description><![CDATA[<var>\text{E}(X^TAX)=tr(A\Sigma)+\mu^T A \mu </var><div>where X is a p-dimensional random variable with mean and covariance&nbsp;</div><var>\text{E}(X)=\mu, \text{Cov}(X)=\Sigma</var><div>and A is a p times p constant matrix.</div><div><br></div>]]></description>
         <enclosure url="" />
         <pubDate>2017-01-27 06:56:17 UTC</pubDate>
         <guid>https://padlet.com/mette_langaas/kvaua8nuc1rx/wish/149804428</guid>
      </item>
   </channel>
</rss>
