placestats

Freedom of expression vs. Marriage rate

Fades after adjusting for income

Across 46 countries, Freedom of expression and Marriage rate rise and fall together at r = -0.58 (on a scale from −1 to +1, where 0 means no link). Comparing only countries with similar income (GDP per person) leaves r = -0.61, which could easily be chance (q = 0.080, allowing for the many pairs tested, and allowing for countries in the same region being alike). Caution: leave-one-out range spans 0.15 in r.

Comparing countries across the middle half of marriage rate, 3.7 to 5.33 marriages per 1,000 people, freedom of expression is worse by 0.121 points at the top of that range than the bottom. Comparing only countries with similar national income, the gap is 0.116 points.

Link before adjusting (r)-0.575p = 2.9e-5 · 46 countries
After adjusting for national income-0.612p = 8.0e-6 · likely range [-0.77, -0.39]
p, allowing for regions0.026standard error 0.176 · 5 regions
Check for luck (q)0.080across 12,497 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.

Freedom of expression · index (0-1)link with income +0.36 · moderate
Marriage rate · marriages per 1,000 peoplelink with income -0.06 · independent

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

Every country as a dot

Freedom of expression · index (0-1) →Marriage rate · marriages per 1,000 people →0.0450.981.399.6Argentina: 0.736 index (0-1), 2.79 marriages per 1,000 peopleAustralia: 0.915 index (0-1), 4.89 marriages per 1,000 peopleAustria: 0.918 index (0-1), 5.24 marriages per 1,000 peopleBelgium: 0.969 index (0-1), 4.2 marriages per 1,000 peopleBulgaria: 0.754 index (0-1), 3.9 marriages per 1,000 peopleCanada: 0.933 index (0-1), 2.6 marriages per 1,000 peopleSwitzerland: 0.967 index (0-1), 4.7 marriages per 1,000 peopleChile: 0.926 index (0-1), 2.7 marriages per 1,000 peopleChina: 0.045 index (0-1), 9.6 marriages per 1,000 peopleColombia: 0.81 index (0-1), 1.39 marriages per 1,000 peopleCosta Rica: 0.915 index (0-1), 4.39 marriages per 1,000 peopleCyprus: 0.812 index (0-1), 8.9 marriages per 1,000 peopleCzechia: 0.947 index (0-1), 5.1 marriages per 1,000 peopleGermany: 0.914 index (0-1), 4.7 marriages per 1,000 peopleDenmark: 0.98 index (0-1), 5.34 marriages per 1,000 peopleSpain: 0.843 index (0-1), 3.7 marriages per 1,000 peopleEstonia: 0.969 index (0-1), 5.3 marriages per 1,000 peopleFinland: 0.946 index (0-1), 3.9 marriages per 1,000 peopleFrance: 0.959 index (0-1), 3.6 marriages per 1,000 peopleUnited Kingdom: 0.833 index (0-1), 1.4 marriages per 1,000 peopleGreece: 0.81 index (0-1), 4.2 marriages per 1,000 peopleCroatia: 0.743 index (0-1), 4.7 marriages per 1,000 peopleHungary: 0.493 index (0-1), 6.6 marriages per 1,000 peopleIreland: 0.97 index (0-1), 3.3 marriages per 1,000 peopleIceland: 0.846 index (0-1), 5 marriages per 1,000 peopleIsrael: 0.822 index (0-1), 5.46 marriages per 1,000 peopleItaly: 0.756 index (0-1), 3.2 marriages per 1,000 peopleJapan: 0.847 index (0-1), 4.1 marriages per 1,000 peopleKorea, Rep.: 0.933 index (0-1), 3.7 marriages per 1,000 peopleLithuania: 0.917 index (0-1), 5.7 marriages per 1,000 peopleLuxembourg: 0.957 index (0-1), 3.8 marriages per 1,000 peopleLatvia: 0.932 index (0-1), 6.3 marriages per 1,000 peopleMexico: 0.619 index (0-1), 3.9 marriages per 1,000 peopleMalta: 0.829 index (0-1), 4.8 marriages per 1,000 peopleNetherlands: 0.91 index (0-1), 4 marriages per 1,000 peopleNorway: 0.953 index (0-1), 3.8 marriages per 1,000 peopleNew Zealand: 0.927 index (0-1), 3.68 marriages per 1,000 peoplePoland: 0.917 index (0-1), 4.2 marriages per 1,000 peoplePortugal: 0.899 index (0-1), 3.5 marriages per 1,000 peopleRomania: 0.777 index (0-1), 6.2 marriages per 1,000 peopleRussian Federation: 0.08 index (0-1), 8.5 marriages per 1,000 peopleSlovak Republic: 0.765 index (0-1), 5.4 marriages per 1,000 peopleSlovenia: 0.691 index (0-1), 3.2 marriages per 1,000 peopleSweden: 0.946 index (0-1), 4.6 marriages per 1,000 peopleTurkiye: 0.179 index (0-1), 6.8 marriages per 1,000 peopleUnited States: 0.729 index (0-1), 6.2 marriages per 1,000 peopleCANCHNCOLCYPDNKGBRLVARUSTUR

best-fit line line after adjusting

Four ways to measure the link

MethodrpCountries
Standard (Pearson), not adjusted-0.5752.9e-546
By rank (Spearman), not adjusted-0.2270.12946
Standard (Pearson), adjusted for national income-0.6128.0e-646
By rank (Spearman), adjusted for national income-0.2350.12046

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 46 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: -0.037 (a minus sign means it grew).

How solid is it?

Leaving out one country at a time, r ranges from -0.657 (without CYP) to -0.505 (without CHN). 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: CHN (+0.107).

Fragile: this link may not hold up.
  • leave-one-out range spans 0.15 in r
  • correlation moves sharply once outliers are trimmed

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.

nr
Europe & Central Asia32-0.42

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.

nr
Poorest third16-0.81
Middle third15+0.05
Richest third15-0.53

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.

nr
Christians38-0.46

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 = -0.024 after dropping 5 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 33years. So a link here can’t come from anything about a country that stays the same, such as its history, geography, institutions or culture.

Within countries over time, there is no link that is clearly more than chance (r = -0.056, comparing each country only with itself over the years, and each year only with the same year elsewhere). Whatever the cross-country picture shows, countries whose freedom of expression moved did not tend to see their marriage rate move with it.

Across countries (adjusted)-0.612for comparison
Within countries+0.001each country vs itself
…and vs the same year elsewhere-0.056q = 0.768 · 44 countries
Year-on-year changes-0.034q = 0.573

1,366 country-years (one country in one year), 44 countries, 1990–2022, about 31 years each on average. Share of the variation that happens within countries over time: 41% for Freedom of expression, 34% for Marriage rate. The margins of error allow for each country appearing many times, and for each year’s value being close to the year before.

Year-to-year changes are a cautious test, not a final answer. Looking only at changes from one year to the next removes each country’s own trends. But it also makes measurement mistakes louder, which pulls the results toward zero. A near-zero result here is weak evidence of no link, not proof.

With one measure years behind the other

0.10−0.1-100+10years Marriage rate trails Freedom of expression →lag -10: r = -0.003 (n = 1,077)lag -9: r = 0.011 (n = 1,121)lag -8: r = 0.029 (n = 1,165)lag -7: r = 0.041 (n = 1,209)lag -6: r = 0.030 (n = 1,252)lag -5: r = 0.014 (n = 1,294)lag -4: r = -0.012 (n = 1,331)lag -3: r = -0.024 (n = 1,367)lag -2: r = -0.033 (n = 1,367)lag -1: r = -0.050 (n = 1,367)lag +0: r = -0.056 (n = 1,366)lag +1: r = -0.057 (n = 1,328)lag +2: r = -0.061 (n = 1,289)lag +3: r = -0.068 (n = 1,249)lag +4: r = -0.069 (n = 1,209)lag +5: r = -0.048 (n = 1,168)lag +6: r = -0.027 (n = 1,128)lag +7: r = -0.015 (n = 1,088)lag +8: r = 0.002 (n = 1,047)lag +9: r = 0.014 (n = 1,006)lag +10: r = 0.018 (n = 965)

Same year (lag 0): -0.056. A peak away from zero does not show which comes first. These series change slowly — this year’s value is close to last year’s. That makes the curve smooth and nearly symmetric, whatever produced the data. Even a sharp peak at one lag (a gap of some years) would not prove that one measure changes the other.

The data


index (0-1)
marriages per 1,000 people		Years
Denmark DNK0.985.342025, 2022
Ireland IRL0.973.32025, 2021
Estonia EST0.9695.32025, 2022
Belgium BEL0.9694.22025, 2022
Switzerland CHE0.9674.72025, 2022
France FRA0.9593.62025, 2022
Luxembourg LUX0.9573.82025, 2022
Norway NOR0.9533.82025, 2022
Czechia CZE0.9475.12025, 2022
Sweden SWE0.9464.62025, 2022
Finland FIN0.9463.92025, 2022
Korea, Rep. KOR0.9333.72025, 2022
Canada CAN0.9332.62025, 2020
Latvia LVA0.9326.32025, 2022
New Zealand NZL0.9273.682025, 2022

Coppedge, M. et al., V-Dem Dataset, Varieties of Democracy (V-Dem) Project
OECD Family Database, indicators SF3.1 (marriage and divorce rates) and SF1.2 (children in families); US series before 1990 from the US Census Bureau and CDC/NCHS

Sources

Freedom of expression

Freedom of expression and alternative sources of information index

V-Dem Institute, University of Gothenburg · via Our World in Data · CC BY 4.0 · updated annual

Media censorship, harassment of journalists, and freedom of academic and cultural expression. A part of the electoral democracy index.

Marriage rate

Crude marriage rate

OECD · via Our World in Data · CC BY 4.0 (OECD terms and conditions) · updated annual

Registered marriages in the year per 1,000 people (counted at mid-year), from official records. Couples living together and registered partnerships are left out. So the rate shows how often people marry, and nothing about how many live as couples. New Zealand counts civil unions. Same-sex marriages count in each country's figure from the year it made them legal. This is the only ready-made series that compares countries. It covers only OECD members, about forty countries, nearly all of them rich. So its links with other measures are worked out over only a third of the countries on the site, and adjusting for GDP has less to remove. The low points in 2020 are the pandemic, not a break in the series. But the British and Canadian series stop at 2020, so their latest value is that low point: 1.4 and 2.6, against 3.7 and 3.9 the year before. The links with the governance measures stay the same using pre-pandemic values, or with both countries removed. No "better" direction is set: it describes how people live, not how well a country is doing.

How this was computed

Data used: most recent value in 2010-2025; values come from 2012–2025. 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 5 World Bank regions. The q-value corrects for testing all 12,497 pairs at once, using the Benjamini–Hochberg method. Underlying data last updated DYB 2024. How the country data works · explore Freedom of expression and Marriage rate

This page shows that two measures go together. It does not show that Freedom of expression changes Marriage rate, or the reverse. These figures also describe countries, not individual people. See the ecological fallacy.

More links with Freedom of expression or Marriage rate