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 on April 23, and its replacement, is already up and running.

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

Re: st: Yitzhaki index

From   Nick Cox <>
Subject   Re: st: Yitzhaki index
Date   Fri, 15 Mar 2013 11:38:07 +0000

Please see

and the heading "Precise references please!".  Minimal person (date)
references are deprecated on Statalist.

The literature you allude to has been bedevilled for decades by the
same name for different things and different names for the same thing.
Before you try writing your own code, be sure that what you want is
not obtainable from user-written programs, or at worst by modifying
user-written programs. There is, exceptionally, a manual entry [R[
inequality documenting such publications and there's a wider selection
under -search inequality-.


"Frank Elgar, Dr."

> My dataset contains a group variable (schoolID) and affluence variable
> (FAS).  I want to calculate Yitzhaki's (1979) index of relative
> deprivation for each individual within schools, the reference group. The
> Yitzhaki index is simply the average distance that separates the income of
> each individual from all higher incomes in the group.  As such, feelings
> of deprivation are based on upward comparisons.
> It does not seem that complicated but I cannot sort out the syntax.
> I have been tried things along the lines of
> by schoolID, sort: egen totFAS=total(FAS)
> by schoolID, sort: egen maxFAS=max(FAS)
> by schoolID, sort: egen schoolsize=count(FAS)
> by schoolID, sort: generate
> yitz=(((total(FAS))-FAS)/schoolsize-1)-FAS)/(size-1)
> by schoolID, sort: replace yitz=0 if FAS>=maxFAS
> But this isn't even close. The distances must be based on all higher FAS
> values within each schoolID. Any suggestions?
*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index