Talk:Gini coefficient

From Wikipedia, the free encyclopedia
Jump to: navigation, search
          This article is of interest to the following WikiProjects:
WikiProject Mathematics (Rated C-class, Mid-importance)
WikiProject Mathematics
This article is within the scope of WikiProject Mathematics, a collaborative effort to improve the coverage of Mathematics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
Mathematics rating:
C Class
Mid Importance
 Field: Probability and statistics
One of the 500 most frequently viewed mathematics articles.
This article has comments.
WikiProject Economics (Rated C-class, Mid-importance)
WikiProject icon This article is within the scope of WikiProject Economics, a collaborative effort to improve the coverage of Economics on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
C-Class article C  This article has been rated as C-Class on the project's quality scale.
 Mid  This article has been rated as Mid-importance on the project's importance scale.
 
WikiProject Sociology (Rated C-class, High-importance)
WikiProject icon This article is within the scope of WikiProject Sociology, a collaborative effort to improve the coverage of Sociology on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
C-Class article C  This article has been rated as C-Class on the project's quality scale.
 High  This article has been rated as High-importance on the project's importance scale.
 
WikiProject Statistics (Rated C-class, Low-importance)
WikiProject icon

This article is within the scope of the WikiProject Statistics, a collaborative effort to improve the coverage of statistics on Wikipedia. If you would like to participate, please visit the project page or join the discussion.

C-Class article C  This article has been rated as C-Class on the quality scale.
 Low  This article has been rated as Low-importance on the importance scale.
 
WikiProject Globalization (Rated C-class, Mid-importance)
WikiProject icon This article is within the scope of WikiProject Globalization, a collaborative effort to improve the coverage of Globalization on Wikipedia. If you would like to participate, please visit the project page, where you can join the discussion and see a list of open tasks.
C-Class article C  This article has been rated as C-Class on the project's quality scale.
 Mid  This article has been rated as Mid-importance on the project's importance scale.
 
This article has an assessment summary page.

Gini coefficient of 0.x means what exactly?[edit]

This article would benefit from explaining what a coefficient of 0.x means. It's easy to explain 0 (perfect equality) and 1 (perfect inequality). How about 0.6? We say "The Gini index for the entire world has been estimated by various parties to be between 0.61 and 0.68". It would be nice to continue and say "which means that x % of the population earns y % of income". --Piotr Konieczny aka Prokonsul Piotrus| reply here 09:17, 29 April 2014 (UTC)

Yes, it would be useful but is, unfortunately, not possible. As explained under limitations, the same Gini index can be a result of vastly different income distribution patterns. As a result, only 0 and 1 are easily summarized, whereas all other values can only be understood in terms of other values (i.e., higher Gini = more inequality). Perhaps a comparison can give some perspective in your example: "The Gini index for the entire world has been estimated by various parties to be between 0.61 and 0.68, roughly equal to that of Sierra Leone".No longer a penguin (talk) 12:34, 29 April 2014 (UTC)
@No longer a penguin: While this is not what I was hoping for, it is still quite useful. Could you provide a ref for such analysis (that Gini between 1 and 0 and hard to interpret)? --Piotr Konieczny aka Prokonsul Piotrus| reply here 07:41, 6 May 2014 (UTC)
I'm afraid that it's a bit of OR, based on the examples in the article (and sourced to Table 6 http://www.fao.org/docs/up/easypol/329/gini_index_040EN.pdf), It's difficult to source the absence of easy interpretation.No longer a penguin (talk) 15:28, 8 May 2014 (UTC)
I doubt many readers have sufficient knowledge of Sierra Leone to make that useful. Is there a better known country in the range?--S Philbrick(Talk) 15:13, 14 May 2014 (UTC)
South Africa seems to be around the same level and is better known.No longer a penguin (talk) 07:28, 15 May 2014 (UTC)

Gini for lognormal[edit]

is probably wrong — Preceding unsigned comment added by 89.67.144.78 (talk) 18:53, 5 May 2014 (UTC)

Gini in Template:infobox country[edit]

At present the Gini is a parameter in the {{infobox country}} template. The template example given uses CIA Worldbook Gini data. With this background in mind, can editors tell us which of the dozen+ Gini variants are being described in this article and which are the most accepted. (IOW, this article needs some clarity as to what variants are what.) With this information I hope that the infobox parameter can be better defined, and so I'm posting the inquiry here as a starting point. – S. Rich (talk) 23:27, 5 May 2014 (UTC)

To expand on my question, I see both terms (coefficient and index) used in the article. It looks like they are synonyms, but are they? If they are, the article should stick to one usage. If not, then an explanation is needed. (I think "index" is most often used in the references.) Also, we need a listing of the variations. I see the following: a "population Gini coefficient ('GC')", a "pre-tax income inequality GC", an "income GC", an "opportunity GC", and an "income inequality GC". Then we have a "pre-tax income Gini index ('GI')", an "after-tax GI", a "net income GI", an "income GI" (without the net or tax descriptives), an "education GI", an "education inequity GI", an "opportunity inequality GI", a "wealth GI", a "global GI", and an "individual income-based GI". (These are all derived from the article text.) Are these the variations or what? Thanks. – S. Rich (talk) 04:16, 6 May 2014 (UTC)

Gini "index" and "coefficient" are the same thing. From what I've seen the sources are all over the place, regarding which ones are used (including the CIA WFB, World Bank, Eurostat, and potentially the OECD), the methodologies, and the results. Even the WFB and WB sources are all over the place in terms of latest year for each country, and it's unclear if even such individual sources are using a consistent methodology across national borders or relying on surveys from those nations. If it's the latter then figures aren't even necessarily comparable within the same source. Presumably the Eurostat source uses a consistent methodology, but that doesn't provide global coverage. There doesn't appear to be an outfit that publishes regularly updated Gini figures for the world or even a large chunk of it, much less one with a standardized methodology.
For that reason we should consider whether this index is appropriate for country article info boxes at all. Contrast it with something like GDP, where outfits like the IMF and World Bank publish new global figures each year. While they differ slightly the two sources' results are pretty close to each other and roughly comparable, so it doesn't even make a huge difference if different articles use different sources. But Gini results can change dramatically depending on methodology, as this pre benefit/post benefit OECD report shows. The template currently labels Gini "optional", but it seems to be included in about every country article, misleading readers into thinking they're seeing something internationally comparable. For example, the US page currently uses the US Census number, which is pre tax/benefit, while numerous European articles use Eurostat, which is post tax/benefit. Unless we can agree on a precise version and find a sufficient source, there isn't much value to giving these figures the prominence of info box status and doing so is arguably detrimental. In that event we should delete it from the template and/or start deleting it from country articles. VictorD7 (talk) 05:55, 7 May 2014 (UTC)
Those are good points.
Although gini coefficients are important, I would oppose widespread use in infoboxes until we have numbers that are consistent between pages. bobrayner (talk) 15:48, 8 May 2014 (UTC)
Thanks. This section seeks to prompt improvements to the Gini article and to help frame a discussion on the infobox template talk page. Can this article be improved to describe how the Gini is used by the IMF, CIA WFB, World Bank, Eurostat, etc.? Doing so will help lead to better infobox usage. – S. Rich (talk) 15:54, 8 May 2014 (UTC)

The Gini coefficient varies between 0, which reflects complete equality and 1, which indicates complete inequality (one person has all the income or consumption, all others have none). Graphically, the Gini coefficient can be easily represented by the area between the Lorenz curve and the line of equality. The Gini Index is simply the coefficient expressed as a percentage (coefficient X 100), where zero represents perfect equality and 100, perfect inequality (see this The Index seems to be more widely used today, likely because most people have trouble understanding something expressed as a coefficient. Meclee (talk) 16:36, 8 May 2014 (UTC)

Following up on this, there is only one Gini coefficient. Different sources may report different numbers, but that's because of measurement and collection issues. Also, there is pre-tax and post-tax Gini. This however, is not a reason to leave out reporting of the Gini coefficient. For example, country GDP will be reported differently by different sources, and there is real vs nominal GDP, GDP per capita vs GDP per household, PPP adjusted, etc. But we report GDP, we just have to try to be consistent. LK (talk) 05:18, 20 May 2014 (UTC)
I'm still confused. If there is only one Gini, why are there so many different versions, like the 15 I mentioned above? I not asking to leave out reporting the Gini, but can't the community decide which one is best for usage in articles? The issue need not be resolved here, but a basic understanding and agreement will be helpful for infobox and other usage. Thanks. – S. Rich (talk) 05:37, 20 May 2014 (UTC)
User:Srich32977: Each Gini Index measures the same thing: how much the distribution of income varies from the poorest to the wealthiest members of a society (and everyone in between).
How "income" is calculated, however, varies. Some economists argue that Purchasing Power Parity, for example (which is basically how much a certain amount of money will allow you to buy in a given country -- though it is important not to conflate this with inflation -- a dollar would have a higher purchasing power parity in Somalia than the United States), should taken into account. Others argue that age needs to be taken into account in calculating the index (since a country with a relatively old populace will have more retirees who have no income). But the basic aim is uniform. Steeletrap (talk) 20:08, 22 May 2014 (UTC)
The basic aim is uniform, but is there a basic result that allows for Gini comparisons between countries? If not, then the Gini should not be used in WP for comparisons. If yes, then which Gini is best to use? – S. Rich (talk) 21:10, 22 May 2014 (UTC)
The situation with GDP is very similar. GDP is what we usually use to measure living standards, but there are different conceptualizations of exactly what to use. There is PPP vs non-PPP adjusted GDP, and GDP per capita vs household GDP, there are other more obscure inconsistencies. We don't resolve the problem by not reporting GDP. Instead, we pick the most commonly used definition(s) from the most reliable sources, and report what they say. On pages about GDP, we also report the methodologies that the reporting organizations use. LK (talk) 07:25, 28 May 2014 (UTC)
My question (and problem) remains: Which is the most commonly used definition and which is the most reliable source? If different commonly used definitions from different reliable sources are put into templates for different articles, what good is the template or Gini? That is, an infobox template used for one country's article might have different definitions & sources compared to another country's infobox. (Hence, the presentation of different Gini indexes in different articles is subject to misuse.) Is it fair to say that the different conceptualizations make it impossible to use one standard conceptualization in all templates/infoboxes? If so, please say so. I'd like to get clarification so that infobox clarification can be achieved. – S. Rich (talk) 19:00, 28 May 2014 (UTC)
Yeah, it's worth repeating that just because something may be article worthy doesn't make it info box worthy. Gini is different than GDP for reasons laid out above involving standardization of methodology (mostly just two GDP types, with one emphasized for international comparisons) and regular publishing of global scope. VictorD7 (talk) 08:52, 30 May 2014 (UTC)