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: nlsuraids returned 199, please help


From   Alex Olssen <alex.olssen@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: nlsuraids returned 199, please help
Date   Sun, 8 May 2011 10:43:22 +1200

If you have 84 observations per equation would you still be
identified?  It seems to me the answer is yes.
You can write an ml program to get around this.  On the other hand you
could try and adjust

nlsur.ado  in base.

It seems to me that the line which produces the error "fewer
observations than parameters" is taking
N = number of observations in any equation

but I think that in this case it should be
N = number of observations per equation * number of equations

Any thoughts would be appreciated.

Alex

On 8 May 2011 03:45, ABDULFATAH S, ADAM <bihiabdul@yahoo.com> wrote:
> Dear Brian,
> Thank you very much. I really appreciate your help.
> It seems it is working, as I am now getting this: "cannot have fewer observations than parameters". This is because i am using an aggregated panel data with 84 observations while I have 88 parameters in my model. Since I have the same data which is not aggregated, I am going to use that and hope it will work this time.
> I will, of course, let you know if there is still a problem.
>
> Best Regards,
> Abdul
>
>
>
> --- On Sat, 5/7/11, Brian P. Poi <brian@poiholdings.com> wrote:
>
>> From: Brian P. Poi <brian@poiholdings.com>
>> Subject: Re: st: nlsuraids returned 199, please help
>> To: statalist@hsphsun2.harvard.edu
>> Date: Saturday, May 7, 2011, 7:53 AM
>>
>> On 05/07/2011 06:14 AM, ABDULFATAH S, ADAM wrote:
>> > Dear Brian,
>> > Thank you very much for your help.
>> > After correcting the errors you identified, I still
>> have the same error.
>> >
>> > capture program drop nlsuraids
>> > quietly: program define nlsuraids
>> >     version 10.0
>> >     syntax varlist (min=24 max=24) if,
>> at(name)
>> >     tokenize `varlist'
>> >     args w1 w2 w3 w4 w5 w6 w7 w8 w9 w10
>> w11 lnp1 lnp2 lnp3 ///
>> >     lnp4 lnp5 lnp6 lnp7 lnp8 lnp9 lnp10
>> lnp11 lnp12 lnexp ///
>> >     tempname a1 a2 a3 a4 a5 a6 a7 a8 a9
>> a10 a11 a12
>>
>> You added a line-continuation mark where you didn't need
>> one, after "lnexp".  The last three lines should be
>>
>>    args w1 w2 w3 w4 w5 w6 w7 w8 w9 w10 w11
>> lnp1 lnp2 lnp3 ///
>>         lnp4 lnp5 lnp6 lnp7 lnp8 lnp9
>> lnp10 lnp11 lnp12 lnexp
>>    tempname a1 a2 a3 a4 a5 a6 a7 a8 a9 a10
>> a11 a12
>>
>> > I believe there is some punctuation or
>> misspecification somewhere
>> in the program, unfortunately I cant see where. It would
>> also be nice
>> if you give me 'shortcut' tips on how to identify such
>> errors easily
>> (if such tips are available) without going over the whole
>> program every
>> time.
>>
>> Before calling -nlsur-, type in
>>
>>    . set trace on
>>    . set tracedepth 4
>>
>> Then issue your -nlsur- command.
>>
>> Scroll up a bit in the results window, and with your
>> program (before including my latest fix) you'll see
>>
>>
>>       - args w1 w2 w3 w4 w5 w6 w7 w8 w9 w10
>> w11 lnp1 lnp2 lnp3 lnp4 lnp5 lnp6 l
>> > np7 lnp8 lnp9 lnp10 lnp11 lnp12 lnexp tempname a1 a2
>> a3 a4 a5 a6 a7 a8 a9 a10
>> >  a11 a12
>>       - scalar `a1'=`at'[1,1]
>>       = scalar =__000003[1,1]
>>
>> ------------------------------------------------------- end
>> nlsuraids ---
>>     - }
>>
>>
>> The fact that the last command (-scalar-) didn't recognize
>> `a1' and the fact that tempname occurred right after lnexp
>> was enough to tell me where to look.  Then I saw that
>> you had an extra /// where it shouldn't have been.
>>
>> Once your program is running, you can type
>>
>>    . set trace off
>>
>> to turn the debugging messages off.  See -help trace-
>> for more information.
>>
>>    -- Brian Poi
>>    -- brian@poiholdings.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/
>>
>
> *
> *   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