GMM estimation

[Kuda Makoni]

I am trying to run one of the examples from the stata manual

. use http://www.stata-press.com/data/r13/docvisits
. gmm (docvis - exp({xb:private chronic female income} + {b0})),

but i keep getting the following error message


Model not identified. There are more parameters than instruments.


What am i doing wrong?

[Stephen Jenkins]

Please re-read the FAQ (hit the black bar at the top of the page) and note the advice about how to best elicit helpful responses. Please show us everything that you typed into Stata and everything that you get back, and report this using CODE delimiters. (If you don't know what that means, please re-read the FAQ again.) Moreover, if you're not using the current version of Stata (14), you should be telling us -- again see the FAQ. The point is that, on the basis of the information you've provided so far, it's virtually impossible for anyone to assess what the problem might be. Moreover, which Stata manual are you referring to (and which pages?). Is your sample gmm code one of the examples shown there or something different?

In Stata 14, I get the following:

. use http://www.stata-press.com/data/r13/docvisits

. de

Contains data from http://www.stata-press.com/data/r13/docvisits.dta
  obs:         4,412                         
 vars:            10                          28 Mar 2013 12:14
 size:        75,004                         
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
              storage   display    value
variable name   type    format     label      variable label
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
docvis          int     %8.0g                 number of doctor visits
age             float   %9.0g                 Age in years / 10
income          float   %9.0g                 Income in $ / 1000
female          byte    %8.0g                 = 1 if female
black           byte    %8.0g                 = 1 if black
hispanic        byte    %8.0g                 = 1 if hispanic
married         byte    %8.0g                 = 1 if married
physlim         byte    %8.0g                 = 1 if physical limitation
private         byte    %8.0g                 = 1 if private insurance
chronic         byte    %8.0g                 = 1 if a chronic condition
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Sorted by:

. gmm (docvis - exp({xb:private chronic female income} + {b0}))
model is not identified; there are more parameters, 5, than instruments, 1
r(481);

This suggests that you haven't specified enough instruments

[Kuda Makoni]

Thank you for the advice, i am using stata 13 and i get the same error message that you are getting, how do i increase the number of instruments ?

http://www.stata.com/manuals13/rgmmp...postestimation

I have also attached the link to the code in the manual i am trying to replicate

[Sherry Lee]

Hi Kuda Makoni, I think you mistyped the command. The right one should be: "gmm (docvis - exp({xb:private chronic female income} + {b0})), instruments(private chronic female age black hispanic) onestep"