<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=us-ascii">
<META content="MSHTML 6.00.2900.3059" name=GENERATOR></HEAD>
<BODY>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007>Hello,</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>I have some
questions related to the ExpectationMaximizationMixtureModelEstimator
class.</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007> I have been
running the example code provided for this algorithm and according to the
example the </SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>standard deviation
for the two Guassian components are chosen as (both) 30 when generating the
sample data points. The initializiation values for the standard deviations for
the EM algorithm are 800, and 850.</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>After running the
example program (number of iterations=200) the results are as the following
:</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>Cluster
[0]</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>Parameters:
[101.886 , 782.963]</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007>Proportion:0.5</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007>Cluster[1]</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>Parameters:[198.538,
951.226]</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>Proportion:
0.49</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>Does that mean that
the standard deviation has not been estimated correctly and the program has to
run more iterations to converge to correct answers for the standard deviations?
And this brings me to my main question:</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>Is there a
built-in way to choose another rule for stopping the EM algorithm,
other than giving it a fixed number of iterations, for example
setting a threshold for result error rates or some other stopping rules? Or
shall I call the estimator inside a loop and keep checking the results
untill satisfactory? </SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>I appreciate your
help and any explanation.</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN class=094114122-20062007>Thanks a
lot</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007>Tina</SPAN></FONT></DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV>
<DIV><FONT face=Arial size=2><SPAN
class=094114122-20062007></SPAN></FONT> </DIV></BODY></HTML>