<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/171085</link>
    <title>MATLAB Central Newsreader - ordered probit model</title>
    <description>Feed for thread: ordered probit model</description>
    <language>en-us</language>
    <copyright>&amp;copy;1994-2012 by MathWorks, Inc.</copyright>
    <webmaster>webmaster@mathworks.com</webmaster>
    <generator>MATLAB Central Newsreader</generator>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <ttl>60</ttl>
    <image>
      <title>MathWorks</title>
      <url>http://www.mathworks.com/images/membrane_icon.gif</url>
    </image>
    <item>
      <pubDate>Tue, 17 Jun 2008 14:10:21 -0400</pubDate>
      <title>ordered probit model</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/171085#437890</link>
      <author>sujata panday</author>
      <description>Hi,&lt;br&gt;
&lt;br&gt;
I want to estimate an ordered probit model in matlab. I &lt;br&gt;
have three categories so the dependent variable is not &lt;br&gt;
simply binary. I think the function mnrfit is the right one &lt;br&gt;
for it. But I do not want it to include an intercept term &lt;br&gt;
which it automatically does. The glmfit function allows one &lt;br&gt;
to disable the constant term. Is it possible to do &lt;br&gt;
something like this too for the mnrfit function?&lt;br&gt;
&lt;br&gt;
Or are there other functions within Matlab that i can use &lt;br&gt;
to estimate an ordered probit model.&lt;br&gt;
&lt;br&gt;
Regards&lt;br&gt;
Sujata</description>
    </item>
    <item>
      <pubDate>Wed, 18 Jun 2008 20:38:02 -0400</pubDate>
      <title>Re: ordered probit model</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/171085#438220</link>
      <author>sujata panday</author>
      <description>&lt;br&gt;
It appears that matlab mnrfit function automatically omits &lt;br&gt;
the constant term when ordinal data is chosen. &lt;br&gt;
&lt;br&gt;
&quot;sujata panday&quot; &amp;lt;sujatagp@gmail.com&amp;gt; wrote in message &lt;br&gt;
&amp;lt;g38gkd$e7e$1@fred.mathworks.com&amp;gt;...&lt;br&gt;
&amp;gt; Hi,&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; I want to estimate an ordered probit model in matlab. I &lt;br&gt;
&amp;gt; have three categories so the dependent variable is not &lt;br&gt;
&amp;gt; simply binary. I think the function mnrfit is the right &lt;br&gt;
one &lt;br&gt;
&amp;gt; for it. But I do not want it to include an intercept term &lt;br&gt;
&amp;gt; which it automatically does. The glmfit function allows &lt;br&gt;
one &lt;br&gt;
&amp;gt; to disable the constant term. Is it possible to do &lt;br&gt;
&amp;gt; something like this too for the mnrfit function?&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Or are there other functions within Matlab that i can use &lt;br&gt;
&amp;gt; to estimate an ordered probit model.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Regards&lt;br&gt;
&amp;gt; Sujata</description>
    </item>
    <item>
      <pubDate>Fri, 20 Jun 2008 21:20:18 -0400</pubDate>
      <title>Re: ordered probit model</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/171085#438725</link>
      <author>Ketan </author>
      <description>I was trying to use mnrfit for my problem but I am getting &lt;br&gt;
the following error:&lt;br&gt;
&lt;br&gt;
====ERROR====&lt;br&gt;
??? Error using ===&amp;gt; mnrfit&lt;br&gt;
Inputs to mnrfit must be floats, namely single or double.&lt;br&gt;
&lt;br&gt;
Error in ==&amp;gt; mnrfit at 125&lt;br&gt;
dataClass = superiorfloat(x,y);&lt;br&gt;
====ERROR====&lt;br&gt;
&lt;br&gt;
My variable x is double. I tried casting it as single using &lt;br&gt;
x=single(x); command, Still I am getting this error.&lt;br&gt;
&lt;br&gt;
Any help will be much appreciated.&lt;br&gt;
&lt;br&gt;
Regards,&lt;br&gt;
Ketan</description>
    </item>
  </channel>
</rss>

