Decomposing erreygers concentration index - stata...

[Dubile Boko]

Hi there,

I am in the process of writing a research paper. I am using Sierra Leone womens DHS dataset. I have used conindex to compute the concentration index (Erreygers). The variable of interest is binary = Contraceptive use (0=No, 1=Yes).

I would like to know if there's anyone who might have a do-file which computes the decomposition of the Erreygers concentration index (using the Wealth Index and Education as the socioeconomic variables). I want to decompose the index to further illustrate the contribution of certain background factors to inequality.

If anyone has worked on something similar, please let me know - or preferably send your do-file so that I can try to adapt it for my research. Thank you.

[Roos Hout]

I have the same question...

[Roos Hout]

Did you already succeed?

[Geha Khanal]

I am facing the same issue!

[Zahrah Rafique]

Hi,
DId anyone of you figure out a way? I need help with this issue

[FernandoRios]

Hi Zahrah,
Perhaps the following paper may be of help:
https://www.sciencedirect.com/scienc...67629616300066
And, the command "rifhdreg" (ssc install rif), or -rifireg- (From the authors of the paper above) implements this.
HTH

[atta asif]

Hi everybody
for measuring inequality through erreygers methodology you may use the following STATA code

conindex Vaccinated [aw=weight], rank(v106) bounded limits(0 1) erreygers
sca CI = r(CI)
global X M_Empow2 M_Empow3 Water_T2 Toilet_T2 Region2 Region3 Region4 Region5 Region6
Region7 Region8 Resid2 W_Index2 W_Index3 M_Edu2 M_Edu3 P_Edu2 P_Edu3 Brea
stfeeding2 C_Gend2 Mat_Age2 Mat_Age3 Mat_Age4
qui sum Vaccinated [aw=weight]
sca m_y=r(mean)
qui glm Vaccinated $X [aw=weight], family(binomial) link(probit)
qui margins , dydx(*) post
foreach x of varlist $X {
sca b_`x'=_b[`x']
}
foreach x of varlist $X {
qui{
conindex `x' [aw=weight], rank(v106) bounded limits(0 1) erreygers
sca CI_`x' = r(CI)
sum `x' [aw=weight]
sca elas_`x' = 4*(b_`x' * r(mean))
sca contri_`x' = elas_`x' * CI_`x'
sca prcnt_`x' = (contri_`x'/CI)*100
}
di "`x' elasticity:", elas_`x'
di "`x' concentration index:", CI_`x'
di "`x' contribution:", contri_`x'
di "`x' percentage contribution:", prcnt_`x'
}

best wishes
Atta Asif

[Nguyen Anh Tuyet]

Dear Asif
Thank you so much for such important codes for this issue. I would like to ask for the official source of these codes for reference!
Thanks you

[Kateryna Kravchenko]

Dear Nguyen Anh Tuyet,

I guess, Atta Asif might have referred to the decomposition method described in "Analyzing Health Equity Using Household Survey Data" by O'Donnell et al. (particularly, chapter 13):
http://siteresources.worldbank.org/I...quityFINAL.pdf

[atta asif]

yes, of course

[Laura Rossouw]

Dear Atta Asif

Is it possible to calculate the statistical significance of the elasticity, concentration index and contribution using this code?

Thanks in advance

[Laura Rossouw]

I've managed to figure out: See this excerpt from https://journals.plos.org/plosone/ar...type=printable ."As there is no analytical expression for the computation of the standard errors for the contributions generated from Eq (4) and since the Stata bootstrap prefix command does not work [12, 36], a bootstrapping technique was used to generate the standard errors for the absolute contributions. Whilst taking into account the data’s sampling structure we applied the bootstrapping method as described in Efron et al. and Efron [37, 38] and applied in Ataguba et al. [36]. Bootstrapping allows us to assess sampling variability and obtain statistical inference on the results from the decomposition [39]. A total of 500 replications were used to estimate the standard errors"

And the following link for bootstrapping standard errors: https://www.stata.com/features/overv...nd-estimation/

[Magashi Joseph]

Dear FernandoRios et al.
I am estimating concentration Erreygers index using the conindex using the following command:

conindex  stunting [pw=wgt], rankvar(wealth_index)  erreygers bounded limits(0 1) cluster(v001) compare(year)

The results are as follows:

                                    
Index:            No. of    obs.    Index value    Robust std.    error    p-value     
                                    
Erreygers    norm.    CI    15743        -.13980342    .01632168        0.0000

For groups:


CI for group 1: year = 2009

                                        
Index:    No.    of    obs.    Index    value    Robust    std.    error    p-value     
                                        
no observations
r(2000);

What could possibly explain the reason for having no observation when wanting to compare the concentration index between years ??

[FernandoRios]

Difficult to say. The first answer would be that you do not have observations for 2009.
what happens when you do the following:
tabstat stunting wgt wealth_index v001, by(year) stats(min n)

[Magashi Joseph]

Dear FernandoRios

Thank you very much for your response. After using the suggested command I found that there were missing values for v001 and after fixing it, I have been able to calculate the CI and compared by years.