Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: estimating distribution functions from Kernel densities


From   "Ben Jann" <ben.jann@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: estimating distribution functions from Kernel densities
Date   Fri, 10 Oct 2008 12:51:51 +0200

mm_kint() provides analytic integrals for a number of specific kernel
functions. It cannot be used to integrate over an empirical density
function.
ben

On Fri, Oct 10, 2008 at 2:30 AM, Henrique Neder <hdneder@ufu.br> wrote:
> I think that programs svylorenz, inequal, calculate inequality measures
> directly from the data, for example, a sequence of observations of income. I
> want to use the DFL method to decompose the effects of the minimum wage and
> the characteristics of workers. For this, obtained through this method is a
> counterfactual Kernel density function. After obtaining this function, I
> desire from the same function (and not directly from my observed income
> data) to obtain some measures of inequality, as the difference between the
> ninth decile and the first decile, the Theil index and the Gini index, as is
> done in the Dinardo, J., NM Fortin, and T. Lemieux (1996) article. For the
> first measure (difference between deciles) and I think also for the other
> two, is necessary to obtain the cumulative distribution function related to
> the Kernel density function. For this I need a procedure in Stata to
> integrate the kernel density function. I discovered that in the set of
> commands named moremata there is a code (mm_kint()) that apparently
> integrates Kernel density functions. This is the right path?
>
> Regards
>
> Henrique Neder
>
> -----Mensagem original-----
> De: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] Em nome de Austin Nichols
> Enviada em: quinta-feira, 9 de outubro de 2008 18:05
> Para: statalist@hsphsun2.harvard.edu
> Assunto: Re: st: estimating distribution functions from Kernel densities
>
> Henrique Neder <hdneder@ufu.br> :
> I think you need to be more clear about what you mean to do. The DFL
> approach reweights the data to obtain the counterfactual density.  If
> you are interested in an inequality measure for the reweighted
> distribution, can't you just compute the measure using your new
> weights, using e.g. a program by Stephen Jenkins et al. (findit
> svygei, findit ineqdeco)?
>
> DiNardo, J., N.M. Fortin, and T.Lemieux (1996) "Labour Market
> Insitutions and the Distribution of Wages, 1973-1992: A Semiparametric
> Approach," Econometrica, 64(5): 1001-1044.
>
>
> On Thu, Oct 9, 2008 at 4:52 PM, Henrique Neder <hdneder@ufu.br> wrote:
>> Dear Stata listers
>>
>>
>> I am studying the methodology of decomposition of Dinardo, Fortin and
>> Lemieux, known as Dfl. I need to estimate the inter-quantile deviation,
> the
>> Gini index and the Theil index for Kernel density functions. There would
> be
>> some method (for example, numerical integration) to do this using Stata?
>>
>> Henrique Neder
> *
> *   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   |   What's new   |   Site index