Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

RE: st: why i can not test my paramerters?


From   "Martin Weiss" <[email protected]>
To   <[email protected]>
Subject   RE: st: why i can not test my paramerters?
Date   Mon, 13 Sep 2010 15:59:44 +0200

<>

-testparm- requires a -varlist-, as its help file shows. 

Use this syntax:

***********
sysuse auto, clear
gmm (mpg - {b1}*gear_ratio - {b2}*turn - {b0}), inst(gear_ratio turn) coefl
test ([b1]:_cons=2.5) ([b2]:_cons=-.8)
***********

Admittedly, -coeflegend- is not as much of a help here as initially thought.

HTH
Martin


-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of oliazim
Sent: Montag, 13. September 2010 15:45
To: [email protected]
Subject: Re: st: why i can not test my paramerters?

The error is again:

 estimates store conditional

 testparm _b[a0:_cons]
variable _b not found
r(111);

Though I have:
Conditional coef
----------------------------------------------------------------------------
--
             |      Coef.  Legend
-------------+--------------------------------------------------------------
--
         /a0 |   241.2715  _b[a0:_cons]
         /b1 |   1.542446  _b[b1:_cons]
      /b_cpi |   .0225705  _b[b_cpi:_cons]
      /b_prr |   .0766196  _b[b_prr:_cons]
      /b_oil |   .0254665  _b[b_oil:_cons]
      /b_ind |   .0019989  _b[b_ind:_cons]
----------------------------------------------------------------------------
--
HAC standard errors based on Bartlett kernel with 1 lags.
Instruments for equation 1: worldindex cpi1 prr1 woil_price1 c_industprod1
    _cons


13.09.10, 17:27, "Martin Weiss" <[email protected]>:

> 
>  <>
>  
>  " Unfortunatly option -coeflegend- does  not work"
>  
>  
>  What exactly does not work? What is the error message? The example works
>  like a charm:
>  
>  
>  ***********
>  sysuse auto, clear
>  gmm (mpg - {b1}*gear_ratio - {b2}*turn - {b0}), instruments(gear_ratio
turn)
>  coeflegend
>  ***********
>  
>  
>  HTH
>  Martin
>  
>  
>  -----Original Message-----
>  From: [email protected]
>  [mailto:[email protected]] On Behalf Of oliazim
>  Sent: Montag, 13. September 2010 15:24
>  To: [email protected]
>  Subject: Re: st: why i can not test my paramerters?
>  
>  Hi Maarten,
>  
>  Unfortunatly option -coeflegend- does  not work but i get all the names
for
>  my coefficients:
>  
>   gmm
>
(Conditional:indexprem_c-{a0}-worldindex*{b1}-worldindex*cpi1*{b_cpi}-worldi
>  ndex*prr1*{b_prr}
>  -worldindex*woil_price1*{b_oil}-worldindex*c_industprod1*{b_ind}),
>  instruments(Conditional: worldindex cpi1 prr1 woil_price1 c_industprod1)
>  wmatrix(hac bartlett 1) variables(worldindex cpi1 prr1 woil_price1
>  c_industprod1) 
>  > title(Conditional coef)
>  
>  Conditional coef
>
----------------------------------------------------------------------------
>  --
>               |                 HAC
>               |      Coef.   Std. Err.      z    P>|z|     [95% Conf.
>  Interval]
>
-------------+--------------------------------------------------------------
>  --
>           /a0 |   241.2715    249.316     0.97   0.333     -247.379
>  729.9219
>           /b1 |   1.542446   .8000236     1.93   0.054    -.0255714
>  3.110463
>        /b_cpi |   .0225705   .0082786     2.73   0.006     .0063446
>  .0387963
>        /b_prr |   .0766196   .0307461     2.49   0.013     .0163584
>  .1368808
>        /b_oil |   .0254665   .0115072     2.21   0.027     .0029128
>  .0480203
>        /b_ind |   .0019989   .0120944     0.17   0.869    -.0217057
>  .0257036
>
----------------------------------------------------------------------------
>  --
>  
>  
>   estimates table Conditional
>  
>  Variable   Conditional   
>  
>  a0           
>  _cons   241.27148     
>  
>  b1           
>  _cons    1.542446     
>  
>  b_cpi        
>  _cons   .02257047**   
>  
>  b_prr        
>  _cons   .07661963*    
>  
>  b_oil        
>  _cons   .02546653*    
>  
>  b_ind        
>  _cons   .00199891     
>  
>  legend: * p<.05; ** p<.01; *** p<.001
>  
>   estimates store Conditional
>  
>   testparm _est_Conditional
>  no such variables
>  r(111);
>  
>   testparm _est_Conditional, equal equation(Conditional)
>  equation Conditional not found
>  r(303);
>  
>   estimates store Conditional
>  
>   testparm worldindex cpi1 prr1 woil_price1 c_industprod1
>  no such variables
>  r(111);
>  
>   testparm worldindex
>  no such variables
>  r(111);
>  
>  Though I have:
>  
>   estimates dir Conditional
>  
>  -------------------------------------------------------
>          name | command      depvar       npar  title 
>  -------------+-----------------------------------------
>   Conditional | gmm          no depvar       6  
>  -------------------------------------------------------
>  
>  
>  13.09.10, 15:57, "Maarten buis" :
>  
>  > --- On Mon, 13/9/10, oliazim wrote:
>  >  > Whatever model i try i can not make the postestimation
>  >  > tests. I save my results in the memory but when i implement
>  >  > the test the program says i do not have such the model (results) in
>  >  > the memory:
>  >  > 
>  >  >  gmm
>  >  >
>
(Conditional:indexprem_c-{a0}-worldindex*{b1}-windex_cpi*{b_cpi}-windex_prr*
>  {b_prr}
>  >  > -windex_oil*{b_oil}-windex_indust*{b_ind}), 
>  >  > instruments(Conditional: worldindex windex_cpi windex_prr
>  >  > windex_oil windex_indust) wmatrix(hac bartlett 1)
>  >  > warning: 46 missing values returned for equation 1 at
>  >  > initial values
>  >  > 
>  >  >  testparm windex_cpi windex_prr windex_oil windex_indust,
>  >  > equation(Conditional)
>  >  > equation Conditional not found
>  >  > r(303);
>  >  > 
>  >  >  testparm worldindex indexprem_c windex_cpi windex_prr
>  >  > windex_oil windex_indust
>  >  > no such variables
>  >  > r(111);
>  >  
>  >  The reason is because you got the names of the parameters
>  >  wrong. Add the option -coeflegend- to your -gmm- command
>  >  to see how the coefficients are exactly named.
>  >  
>  >  Hope this helps,
>  >  Maarten
>  >  
>  >  --------------------------
>  >  Maarten L. Buis
>  >  Institut fuer Soziologie
>  >  Universitaet Tuebingen
>  >  Wilhelmstrasse 36
>  >  72074 Tuebingen
>  >  Germany
>  >  
>  >  http://www.maartenbuis.nl
>  >  --------------------------
>  >  
>  >  
>  >        
>  >  
>  >  *
>  >  *   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/
>  
>  *
>  *   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/

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index