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]

Re: st: time series analysis ommited variables bias/specification error testing


From   Robert A Yaffee <bob.yaffee@nyu.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: time series analysis ommited variables bias/specification error testing
Date   Sat, 14 May 2011 17:06:11 -0400

Muhammad,
   As for the bias introduced by the omitted variable,  you would have
to figure out what that variable is to see how the estimation is 
undermined by it. 
   The direction of bias will depend on the correlation of the 
explanatory variable with the missing variable.  However, if your
specification stems from incorrect functional form, you would want
to run a sensitivity analysis using the missing interaction or power
to determine the significance, direction, and magnitude of the bias.
    Regards,
          Robert
Robert A. Yaffee, Ph.D.
Research Professor
Silver School of Social Work
New York University

Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2009.pdf

CV:  http://homepages.nyu.edu/~ray1/vita.pdf

----- Original Message -----
From: Muhammad Anees <aneesmkhattak@gmail.com>
Date: Saturday, May 14, 2011 3:07 am
Subject: st: time series analysis ommited variables bias/specification error testing
To: statalist@hsphsun2.harvard.edu

> Hi
> 
> I am just wondering if my question is too basic although my confusion
> seems as legitimate to me.
> I have to check if my time series model y=ao+b1x1+b2x2+b3x3+b4x4+error
> has or has not an omitted variable bias or specification error against
> the three alternative
> 
> (1)   y=ao+b1x1+b2x1^2+b3x2+b4x3+b5x4+error
> (2)   y=ao+b1x1+b2x2+b3x3+b4x4+b5x5+error
> (3)   y=ao+b1x1+b2x1^2+b3x2+b4x3+b5x4+b6x5error
> 
> What econometric tests Stata can offer and what can be the possible
> interpretation the testing procedure, even though the interpretation
> will depends on the testing technique? Now if if I have used the first
> model and have tested for cointegation and granger causality, what
> implication the has been the result of ommiting variables or
> specifying incorrect model.
> 
> Thanks in advance for your time and suggestions?
> 
> 
> ---
> Best,
> 
> 
> ---------------
> Anees
> *
> *   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/
*
*   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