Accessing Results from GMM estimation in other lines of code

[Chuck Hotelier]

If I were to run a linear regression, say

reg lyi lki lli, robust

then I could access the coefficients in future lines of code with

_b[lki]

or

 _b[lli]

.

is there a succinct way to obtain the same for specific coefficients from a GMM regression? I understand that the coefficients are somehow stored in e(b) but

disp e(b)

disp e(b)[1]

disp e(b){rho}

all result in a type mismatch. The gmm estimation function I am using looks like this:

gmm (ly - ( {rho}*lly + {beta0} + {betak}*(lk - {rho}*llk) + {betal}*(ll - {rho}*lll) ) ), instruments(lk llk lll logwag loglwag) nolog

I want this so I can plug the labor elasticity from the GMM into a function to estimate markups.

Thanks in advance for your help!

[Frode Andre]

Perhaps this can work:

gmm (ly - ( {rho}*lly + {beta0} + {betak}*(lk - {rho}*llk) + {betal}*(ll - {rho}*lll) ) ), instruments(lk llk lll logwag loglwag) nolog coeflegend

But then the results are removed.

[Andrew Musau]

There is nothing special about gmm in terms of its operation as an estimation command. The coefficients can be accessed in the usual way.

sysuse auto, clear
gmm (mpg - {b1}*gear_ratio - {b2}*turn - {b0}), instruments(gear_ratio turn)
di _b[/b1]
mat l e(b)
di e(b)["y1", "b2:_cons"]

Res.:

. gmm (mpg - {b1}*gear_ratio - {b2}*turn - {b0}), instruments(gear_ratio turn)

Step 1
Iteration 0:  GMM criterion Q(b) =  471.67875  
Iteration 1:  GMM criterion Q(b) =  3.058e-21  
Iteration 2:  GMM criterion Q(b) =  2.545e-31  

Step 2
Iteration 0:  GMM criterion Q(b) =  1.691e-32  
Iteration 1:  GMM criterion Q(b) =  1.691e-32  (backed up)

note: model is exactly identified.

GMM estimation 

Number of parameters =   3
Number of moments    =   3
Initial weight matrix: Unadjusted                 Number of obs   =         74
GMM weight matrix:     Robust

------------------------------------------------------------------------------
             |               Robust
             | Coefficient  std. err.      z    P>|z|     [95% conf. interval]
-------------+----------------------------------------------------------------
         /b1 |   3.032884   1.501664     2.02   0.043     .0896757    5.976092
         /b2 |  -.7330502    .117972    -6.21   0.000    -.9642711   -.5018293
         /b0 |   41.21801   8.396739     4.91   0.000     24.76071    57.67532
------------------------------------------------------------------------------
Instruments for equation 1: gear_ratio turn _cons

. 
. di _b[/b1]
3.0328836

. 
. mat l e(b)

e(b)[1,3]
            b1:         b2:         b0:
         _cons       _cons       _cons
y1   3.0328836  -.73305019   41.218012

. 
. di e(b)["y1", "b2:_cons"]
-.73305019

.

For extracting elements from a matrix:

help matrix_extraction

[Chuck Hotelier]

This is exactly what I was looking for here. Thank you for the help, Andrew.

There is nothing special about gmm in terms of its operation as an estimation command. The coefficients can be accessed in the usual way.

sysuse auto, clear
gmm (mpg - {b1}*gear_ratio - {b2}*turn - {b0}), instruments(gear_ratio turn)
di _b[/b1]
mat l e(b)
di e(b)["y1", "b2:_cons"]

Res.:

. gmm (mpg - {b1}*gear_ratio - {b2}*turn - {b0}), instruments(gear_ratio turn)

Step 1
Iteration 0: GMM criterion Q(b) = 471.67875
Iteration 1: GMM criterion Q(b) = 3.058e-21
Iteration 2: GMM criterion Q(b) = 2.545e-31

Step 2
Iteration 0: GMM criterion Q(b) = 1.691e-32
Iteration 1: GMM criterion Q(b) = 1.691e-32 (backed up)

note: model is exactly identified.

GMM estimation

Number of parameters = 3
Number of moments = 3
Initial weight matrix: Unadjusted Number of obs = 74
GMM weight matrix: Robust

------------------------------------------------------------------------------
| Robust
| Coefficient std. err. z P>|z| [95% conf. interval]
-------------+----------------------------------------------------------------
/b1 |  3.032884  1.501664 2.02 0.043 .0896757 5.976092
/b2 | -.7330502 .117972 -6.21 0.000 -.9642711 -.5018293
/b0 | 41.21801 8.396739 4.91 0.000 24.76071 57.67532
------------------------------------------------------------------------------
Instruments for equation 1: gear_ratio turn _cons

.
. di _b[/b1]
3.0328836

.
. mat l e(b)

e(b)[1,3]
b1: b2: b0:
_cons _cons _cons
y1 3.0328836 -.73305019 41.218012

.
. di e(b)["y1", "b2:_cons"]
-.73305019

.

For extracting elements from a matrix:

help matrix_extraction