Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Dfactor - Optimization Terminated


From   "Degas Wright" <dwright@cornerstoneadvice.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Dfactor - Optimization Terminated
Date   Wed, 20 Oct 2010 09:53:44 -0400

Statalist members,
I am working with panel data and using the _dfactor_ command in the form
of 


dfactor(D.(r ep mom qer fsr bm np)=,noconstant)(f=,ar(1/2)) if
xticker==`x'

I have created a loop that will perform _dfactor_ for each ticker in my
universe of 1000 stocks.  My objective is to use the dynamic factor
model to estimate future stock returns (i.e. direction and magnitude of
movement). However, I am running into a problem that the _dfactor_ does
not converge to a solution and gives me the following error message:

optimization terminated because of numerical instability: Hessian is not
negative semidefinite

What guidance can you give me with handling this error such as
transformation of variables, reducing the number of variables, or
different autoregressive approach, etc. 

The results are as follows:

                             DFactor  for  xticker: 5
searching for initial values 
(setting technique to bhhh)
Iteration 0:   log likelihood = -331.65736  
Iteration 1:   log likelihood = -291.03732  
Iteration 2:   log likelihood = -280.12209  
Iteration 3:   log likelihood = -280.10965  (backed up)
Iteration 4:   log likelihood = -280.07876  (backed up)
(switching technique to nr)
Iteration 5:   log likelihood =  -280.0696  (not concave)
Iteration 6:   log likelihood = -107.97484  (not concave)
Iteration 7:   log likelihood = -38.628097  (not concave)
Iteration 8:   log likelihood =  108.21357  
Iteration 9:   log likelihood =  127.27167  
Iteration 10:  log likelihood =  132.60344  (not concave)
.
.
Iteration 21:  log likelihood =  134.87566  (backed up)
Iteration 22:  log likelihood =  134.87566  (backed up)
Iteration 23:  log likelihood =  134.87566  (backed up)
optimization terminated because of numerical instability: Hessian is not
negative semidefinite
r(430);

Again, thank you for your assistance.

Degas A. Wright, CFA
Chief Investment Officer
Decatur Capital Management, Inc.
250 East Ponce De Leon Avenue, Suite 325
Decatur, Georgia  30030
Voice: 404.270.9838
Fax:404.270.9840
Website: www.decaturcapital.com

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index