Re: st: QUAIDS with demographic translation

[Khalida Akhtar Choudhury <310543@soas.ac.uk>]

Dear Nick,

I've run the first few commands without the inclusion of demographic
variables and it has worked. I think the error lies some where with
the inclusion of local macro d1, and the inclusion of d1 in the model.

Khalida

On 29 August 2012 13:34, Nick Cox <njcoxstata@gmail.com> wrote:
> This loop
>
> local j 1
>
> forvalues i = 1/$nminus1 {
>
> local w`i' `:word `j' of `varlist''
>
> local `++j'
>
> }
>
> seems unlikely to be what you intend. You don't need two macros to
> loop over a list, and the effect of
>
> local `++j'
>
> is not that of
>
> local ++j
>
> I'd guess that you want
>
> forvalues i = 1/$nminus1 {
>                   local w`i' `:word `i' of `varlist''
> }
>
> In general, this is a long program and I guess that you are not an
> experienced Stata programmer. It is best to use -set trace- and lots
> of -display- statements to go through your program line by line.
>
> Nick
>
>
> On Wed, Aug 29, 2012 at 12:40 PM, Khalida Akhtar Choudhury
> <310543@soas.ac.uk> wrote:
>> Hello,
>>
>> I have tried to code my own do file for QUAIDS with demographic
>> translation. I am using the approach of Gould & Dong (2004). There are
>> two differences between my approach and that of Banks et al. (1997).
>> There is a scalar term representing demographic variables(ti(d)) in
>> the welfare share equation(wi) and the expenditure m* is now dependent
>> on demographic variables.
>>
>> I get error 198, "nlsurquaids returned 198 verify that nlsurquaids is
>> a function evaluator program an error occurred when bootstrap executed
>> estimate."
>>
>> set seed 1
>>
>> global ngoods =3D 4 // no. of goods
>>
>> global nbootstraps =3D 3 // no. of bootstrap replications
>>
>> global anot =3D 6 // alpha_0 parameter
>>
>>
>>
>>
>> global nminus1 =3D $ngoods - 1
>>
>>
>>
>> capture program drop nlsurquaids
>>
>> program nlsurquaids, rclass
>>
>>
>>
>> version 10
>>
>>
>>
>> local nv =3D $ngoods + $nminus1 + 1
>>
>> syntax varlist(min=3D`=3D`nv'' max=3D`=3D`nv'') if, at(name)
>>
>>
>>
>> local j 1
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> local w`i' `:word `j' of `varlist''
>>
>> local `++j'
>>
>> }
>>
>> forvalues i =3D 1/$ngoods {
>>
>> local lnp`i' `:word `j' of `varlist''
>>
>> local `++j'
>>
>> }
>>
>> local lnm `:word `j' of `varlist''
>>
>> local col 1
>>
>> local d1 :word count `demographics'
>>
>> // alpha
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> tempname a`i'
>>
>> scalar `a`i'' =3D `at'[1,`col']
>>
>> local `++col'
>>
>> }
>>
>> tempname a${ngoods}
>>
>> scalar `a${ngoods}' =3D 1
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> scalar `a${ngoods}' =3D `a${ngoods}' - `a`i''
>>
>> }
>>
>> // beta
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> tempname b`i'
>>
>> scalar `b`i'' =3D `at'[1,`col']
>>
>> local `++col'
>>
>> }
>>
>> tempname b${ngoods}
>>
>> scalar `b${ngoods}' =3D 0
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> scalar `b${ngoods}' =3D `b${ngoods}' - `b`i''
>>
>> }
>>
>> // gamma
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> forvalues j =3D 1/$nminus1 {
>>
>> tempname g`i'`j'
>>
>> if `i' > `j' {
>>
>> scalar `g`i'`j'' =3D `g`j'`i''
>>
>> }
>>
>> else {
>>
>> scalar `g`i'`j'' =3D `at'[1, `col']
>>
>> local `++col'
>>
>> }
>>
>> }
>>
>> tempname g`i'${ngoods}
>>
>> scalar `g`i'${ngoods}' =3D 0
>>
>> forvalues j =3D 1/$nminus1 {
>>
>> scalar `g`i'${ngoods}' =3D  `g`i'${ngoods}' - `g`i'`j''
>>
>> }
>>
>> }
>>
>> forvalues j =3D 1/$nminus1 {
>>
>> tempname g${ngoods}`j'
>>
>> scalar `g${ngoods}`j'' =3D `g`j'${ngoods}'
>>
>> }
>>
>> tempname g${ngoods}${ngoods}
>>
>> scalar `g${ngoods}${ngoods}' =3D 0
>>
>> forvalues j =3D 1/${ngoods} {
>>
>> scalar `g${ngoods}${ngoods}' =3D `g${ngoods}${ngoods}' -  ///
>>
>> `g${ngoods}`j''
>>
>> }
>>
>> // lambda
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> tempname l`i'
>>
>> scalar `l`i'' =3D `at'[1,`col']
>>
>> local `++col'
>>
>> }
>>
>> tempname l${ngoods}
>>
>> scalar `l${ngoods}' =3D 0
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> scalar `l${ngoods}' =3D `l${ngoods}' - `l`i''
>>
>> }
>>
>> //omega
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> tempname o`i'
>>
>> scalar `o`i'' =3D `at'[1,`col']
>>
>> local `++col'
>>
>> }
>>
>>
>>
>> quietly {
>>
>> tempvar lnpindex
>>
>> gen double `lnpindex' =3D $anot
>>
>> forvalues i =3D 1/$ngoods {
>>
>> replace `lnpindex' =3D `lnpindex' + `a`i''*`lnp`i''
>>
>> }
>>
>> forvalues i =3D 1/$ngoods {
>>
>> forvalues j =3D 1/$ngoods {
>>
>> replace `lnpindex' =3D `lnpindex' +  ///
>>
>> 0.5*`g`i'`j''*`lnp`i''*`lnp`j''
>>
>> }
>>
>> }
>>
>> tempvar bp
>>
>> gen double `bp' =3D 0
>>
>> forvalues i =3D 1/$ngoods {
>>
>> replace `bp' =3D `bp' + `lnp`i''*`b`i''
>>
>> }
>>
>> replace `bp' =3D exp(`bp')
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> replace `w`i'' =3D `a`i'' + `o`i''*`demographics'
>>
>> forvalues j =3D 1/$ngoods {
>>
>> replace `w`i'' =3D `w`i'' + `g`i'`j''*`lnp`j''
>>
>> }
>>
>> replace `w`i'' =3D `w`i'' +  ///
>>
>> `o`i''*`demographics'+ ///
>>
>> `b`i''*(`lnm' - `lnpindex') + ///
>>
>> `l`i''/`bp'*(`lnm' - `lnpindex')^2
>>
>> }
>>
>> }
>>
>>
>>
>> end
>>
>>
>>
>> // This program fits the QUAIDS model, then it calculates the elasticities
>>
>> // at the sample means.
>>
>>
>>
>> capture program drop estimate
>>
>> program estimate, rclass
>>
>>
>>
>> // Build up nlsur command
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> local vlist `vlist' w`i'
>>
>> local alist `alist' a`i'
>>
>> local blist `blist' b`i'
>>
>> local llist `llist' l`i'
>>
>> local tlist `olist' o`i'
>>
>> }
>>
>> forvalues i =3D 1/$ngoods {
>>
>> local vlist `vlist' lnp`i'
>>
>> }
>>
>> local vlist `vlist' lnexp
>>
>> forvalues i =3D 1/$nminus1 {
>>
>> forvalues j =3D `i'/$nminus1 {
>>
>> local glist `glist' g`i'`j'
>>
>> }
>>
>> }
>>
>> nlsur quaids @ `vlist', ifgnls nequations($nminus1) ///
>>
>> param(`alist' `blist' `glist' `llist'`olist')
>> *
>> *   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/