Re: st: how to code results from ineqdeco into new variable

[Megan Sheahan <megan.sheahan@gmail.com>]

Looks like a fairly old version:

. which ineqdeco
c:\ado\plus\i\ineqdeco.ado
*! version 1.0.1 Stephen P. Jenkins, April 1998   STB-48 sg104
*! Inequality indices and decomposition by population subgroups
*! Syntax: ineqdeco <var> [[w=weight] if <exp> in <range>],
*!              [by(<groupvar>) w s]

How would I go about finding a newer one? I just downloaded the first
one that came up.

Thanks for all of your help and patience.

All the best,
Megan


On Sat, Nov 17, 2012 at 3:37 AM, Nick Cox <njcoxstata@gmail.com> wrote:
> I can't see what the problem is then. Please confirm the version of
> -ineqdeco- you are using by
>
> . which ineqdeco
>
> Nick
>
> On Sat, Nov 17, 2012 at 12:20 AM, Megan Sheahan <megan.sheahan@gmail.com> wrote:
>> "vil" is a double numeric variable; "totasvalall_10" is a long numeric
>> variable.
>>
>>
>> On Fri, Nov 16, 2012 at 6:02 PM, Nick Cox <njcoxstata@gmail.com> wrote:
>>> -ineqdeco- is from SSC.
>>>
>>> Works for me:
>>>
>>> . sysuse auto, clear
>>> (1978 Automobile Data)
>>>
>>> . qui ineqdeco mpg, by(rep78)
>>>
>>> . gen gini = .
>>> (74 missing values generated)
>>>
>>> . qui foreach v in 1 2 3 4 5 {
>>>
>>> . tabdisp rep78, c(gini)
>>>
>>> ----------------------
>>> Repair    |
>>> Record    |
>>> 1978      |       gini
>>> ----------+-----------
>>>         1 |   .0714286
>>>         2 |   .1021242
>>>         3 |   .1152087
>>>         4 |   .1259259
>>>         5 |   .1697372
>>>         . |
>>> ----------------------
>>>
>>> Is -vil- a string variable?
>>>
>>> Nick
>>>
>>> On Fri, Nov 16, 2012 at 10:13 PM, Megan Sheahan <megan.sheahan@gmail.com> wrote:
>>>
>>>> I downloaded the package for ineqdeco and am attempting to make
>>>> village-level (denoted by variable "vil" in my data) gini coefficients
>>>> using a variable in my data set called "totasvalall_10." I am trying
>>>> to do this by running the command ineqdeco by vil, then trying to have
>>>> Stata recall those values and put them into a variable named "gini."
>>>>
>>>> Below is the syntax that was suggested to me, although Stata is unable
>>>> to recall any of the gini coefficients after running the second line.
>>>> When it runs the "replace" line of code, no values are inserted into
>>>> the variable "gini." So, it appears that Stata is not remembering the
>>>> information after running ineqdeco. Am I missing something? I am using
>>>> Stata 11.
>>>>
>>>> generate gini=.
>>>> ineqdeco totasvalall_10, by(vil)
>>>> foreach z in 1111 1112 1113 1114 1211 1221 1222 1311 ///
>>>> 3111 3112 3211 3212 3213 3214 3311 3312 3313 3314 ///
>>>> 3411 3412 3413 3414 3415 3416 3511 3512 4111 4112 4113 4114 ///
>>>> 4115 4116 4211 4212 4221 4222 4223 4224 4231 4232 ///
>>>> 5111 5112 5113 5121 5122 5131 5211 5212 5213 ///
>>>> 5214 5221 5222 5223 5224 5231 5232 5311 5312 5313 5314 6111 ///
>>>> 6112 6121 6122 6131 6132 6221 6222 6223 6224 6231 6232 6233 ///
>>>> 6234 7111 7112 7113 7114 7211 7212 7221 7222 7231 7232 7233 ///
>>>> 7234 7311 7312 7411 7412 7413 7421 7511 7512 7521 7522 7523 ///
>>>> 7524{
>>>> replace gini=r(gini_`z') if vil==`z'
>>>> }
>>>>
>>> *
>>> *   For searches and help try:
>>> *   http://www.stata.com/help.cgi?search
>>> *   http://www.stata.com/support/faqs/resources/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/faqs/resources/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/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/