Do Ethnic diversity and Religious attendance go together across countries?

Across 90 countries the link before adjusting for anything is r = +0.51, on a scale from -1 (opposite) to +1 (in step). A version that uses only each country's rank gives +0.46.

Does the link hold within countries over time, not just across countries?

There are not enough years of data within countries to check this over time.

Does Ethnic diversity cause Religious attendance?

This analysis cannot answer that. It shows only that the two go together. A link between two country measures, adjusted or not, does not show that either one changes the other. Country figures also say nothing about individual people.

Ethnic diversity vs. Religious attendance

Fades after adjusting for income

A country is not a person. Countries where more people are counted as belonging to this group also tend to differ on the other measure, and that is all. It does not follow that the people in the group are the people with the different score. Making that leap is called the ecological fallacy: reading a pattern across places as a fact about individual people. It is the most common misuse of this kind of data. Religion also varies strongly with region, history and national income, so much of what looks religious here is really those. That is what the adjusted figures are for. The religion shares are estimates for two years only, and the survey questions are asked in rounds that can be ten years apart.

Across 90 countries, Ethnic diversity and Religious attendance rise and fall together at r = +0.51 (on a scale from −1 to +1, where 0 means no link). Comparing only countries with similar income (GDP per person) leaves r = +0.38, which could easily be chance (q = 0.26, allowing for the many pairs tested, and allowing for countries in the same region being alike). Caution: direction is not consistent across regions.

Comparing countries across the middle half of ethnic diversity, 0.21 to 0.569 points, religious attendance is 18.1% of respondents higher at the top of that range than the bottom. Comparing only countries with similar national income, the gap is 10.6% of respondents.

Link before adjusting (r)+0.514p = 2.1e-7 · 90 countries

After adjusting for national income+0.375p = 0.000 · likely range [+0.18, +0.54]

p, allowing for regions0.099standard error 0.192 · 7 regions

Check for luck (q)0.263across 13,797 pairs

How to read these.r runs from −1 (one goes up as the other goes down) to +1 (they rise together), and 0 means no link. Adjusting for national income means comparing countries with the same GDP per person, so differences in wealth can’t explain the link. Income is used in percentage terms, since an extra $1,000 means more to a poor country than to a rich one. p is how likely a link this strong would be if there were really none. Below 0.05 means it is unlikely to be chance. Very small values are written in short form: 1.1e-32 means a decimal point followed by 31 zeros and then 11, so very close to zero. The likely range is where the true figure probably lies, and a range that crosses zero means the link could easily be chance. Countries in the same region tend to resemble each other, so the third figure allows for that, which gives a fairer p. The standard error is the typical size of the error in r. Finally, testing this many pairs means some will look strong by luck alone. A q below 0.05 means this link is unlikely to be one of those.

Ethnic diversity · index, 0 to 1link with income -0.37 · moderate

Religious attendance · % of respondentslink with income -0.66 · high

“Link with income” is how closely each measure tracks GDP per person across countries, from −1 to +1.

Every country as a dot

best-fit line line after adjusting

Four ways to measure the link

Method	r	p	Countries
Standard (Pearson), not adjusted	+0.514	2.1e-7	90
By rank (Spearman), not adjusted	+0.462	4.7e-6	90
Standard (Pearson), adjusted for national income	+0.375	0.000	90
By rank (Spearman), adjusted for national income	+0.324	0.002	90

The rank version uses only each country’s place in line, from lowest to highest, so a few extreme countries count for less. The adjusted and unadjusted versions use the same 90 countries: those that report both measures and GDP per person. So the gap between them comes from the adjustment, not from a change in which countries are counted. Drop in the size of r after adjusting: +0.139 (a minus sign means it grew).

How solid is it?

Leaving out one country at a time, r ranges from +0.334 (without HTI) to +0.418 (without POL). The bar above shows that range on a scale from −1 to +1, with the solid line at the full result. The single country that moves r most: POL (+0.043).

Fragile: this link may not hold up.

direction is not consistent across regions

Within each region

Countries are not separate, unrelated cases, and neighbors share a lot. A link that holds inside each region is far more believable than one that shows up only when comparing regions.

	n	r
East Asia & Pacific	12	+0.85
Europe & Central Asia	42	-0.11
Latin America & Caribbean	13	+0.88

By income third

If the link shows up only in the richest third of countries, it is a feature of rich countries, not a general pattern.

	n	r
Poorest third	30	+0.64
Middle third	30	+0.48
Richest third	30	-0.18

By largest religious group

Countries grouped by a label they share, such as main religion, rather than by a number. Groups of fewer than twelve countries are not shown. These groups differ in income, region and history all at once. So a gap between them is a place to start asking questions, not an answer.

	n	r
Christians	55	+0.29
Muslims	24	+0.47

By last european coloniser

	n	r
Never a European colony	15	+0.60
Spain	12	+0.78
United Kingdom	21	+0.27

Without outliers (countries far outside the middle half of countries on either measure, by more than one and a half times the width of that middle half): r = +0.375 after dropping 0 countries.

Two series, one country

Both measures over the years for one country you pick. The two charts are stacked so they share only the years along the bottom.

Loading…

Over time, within countries

Everything above compares countries with each other at one moment. This section compares each country only with itself over 0years. So a link here can’t come from anything about a country that stays the same, such as its history, geography, institutions or culture.

Not enough history inside each country to look at this over time. That needs countries measured for several years in a row, and at least one of these measures is measured too rarely.

The data

	index, 0 to 1	% of respondents	Years
South Africa ZAF	0.856	69%	2013, 2014
Kenya KEN	0.855	84.6%	2013, 2022
Mali MLI	0.852	73.9%	2013, 2010
Nigeria NGA	0.85	90.3%	2013, 2022
Philippines PHL	0.807	81.8%	2013, 2022
Indonesia IDN	0.803	77.8%	2013, 2022
Ethiopia ETH	0.783	93%	2013, 2022
Burkina Faso BFA	0.767	76.9%	2013, 2010
Pakistan PAK	0.748	60.9%	2013, 2022
Iran, Islamic Rep. IRN	0.743	43.2%	2013, 2022
Ghana GHA	0.736	83.8%	2013, 2014
Canada CAN	0.73	16.4%	2013, 2022
Zambia ZMB	0.706	80.9%	2013, 2010
Spain ESP	0.669	22.8%	2013, 2022
Trinidad and Tobago TTO	0.655	57.8%	2013, 2014

Drazanova, L. (2019), Historical Index of Ethnic Fractionalization Dataset (HIEF), Harvard Dataverse, doi:10.7910/DVN/4JQRCL
Haerpfer, C. et al., World Values Survey; EVS, European Values Study

Sources

Ethnic diversity

Ethnic fractionalization index

Lenka Drazanova · CC0 1.0 · updated one edition (2019), annual values 1945-2013

The chance that two people picked at random in a country belong to different ethnic groups, from 0 (everyone in one group) to close to 1 (many small groups). It measures how mixed a country is, not which groups live there. The groups are those each country's own sources use, so where the lines are drawn differs from country to country. Yearly from 1945 to 2013, so the latest value is from 2013. No "better" direction is set.

Religious attendance

Share attending religious services frequently

World Values Survey Association and European Values Study · via Our World in Data · Free for non-commercial use with attribution · updated irregular (survey waves, roughly every 5 years)

The share who attend religious services at least once a month. This measures taking part, not belief or belonging to a religion. Those are three different things, and they can differ sharply. A country can be almost entirely religious by belonging and yet rarely attend anything. No "better" direction is set, and none could be defended. Attendance describes how people live. It does not show whether a country is doing well, and calling either end the good one would be a claim this site has no basis for. The survey runs in waves, not every year, so data for each country are sparse and uneven.

How this was computed

Data used: most recent value in 2010-2025; values come from 2010–2022. To adjust for income, each measure is first predicted from GDP per person (in percentage terms, on a log scale) with a straight-line fit. Only what is left over is then compared. This is called a partial correlation. The line is drawn the standard way (ordinary least squares), which picks the line that comes closest to all the countries at once. The error margins allow for countries in the same region resembling each other, using 7 World Bank regions. The q-value corrects for testing all 13,797 pairs at once, using the Benjamini–Hochberg method. Underlying data last updated DYB 2024. How the country data works · explore Ethnic diversity and Religious attendance

This page shows that two measures go together. It does not show that Ethnic diversity changes Religious attendance, or the reverse. These figures also describe countries, not individual people. See the ecological fallacy.