placestats

Child stunting vs. Researchers

Fades after adjusting for income

Across 109 countries, Child stunting and Researchers rise and fall together at r = -0.52 (on a scale from −1 to +1, where 0 means no link). Comparing only countries with similar income (GDP per person) shrinks it to -0.05, which could easily be chance (q = 0.62, allowing for the many pairs tested, and allowing for countries in the same region being alike). So the first figure mostly shows richer countries differing from poorer ones, not a link between these two things. Caution: correlation moves sharply once outliers are trimmed.

Comparing countries across the middle half of child stunting, 4.6% to 22% of children under 5, researchers is worse by 1,483 per million people at the top of that range than the bottom. Comparing only countries with similar national income, the gap is 180 per million people.

Link before adjusting (r)-0.520p = 6.9e-9 · 109 countries
After adjusting for national income-0.051p = 0.604 · likely range [-0.24, +0.14]
p, allowing for regions0.428standard error 0.059 · 7 regions
Check for luck (q)0.623across 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.

Child stunting · % of children under 5link with income -0.80 · proxy
Researchers · per million peoplelink with income +0.85 · proxy

Both of these rise and fall closely with national income, so a strong link between them before adjusting was close to certain. Read the adjusted figure, not the first one.

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

Every country as a dot

Child stunting · % of children under 5 →Researchers · per million people →1%55.3%1.459,472Angola: 47.7% of children under 5, 18.9 per million peopleAlbania: 7.4% of children under 5, 429 per million peopleArgentina: 10.7% of children under 5, 1,313 per million peopleArmenia: 6.2% of children under 5, 942 per million peopleAustralia: 3.1% of children under 5, 4,569 per million peopleAzerbaijan: 6.8% of children under 5, 1,663 per million peopleBurundi: 55.3% of children under 5, 22.5 per million peopleBelgium: 2.6% of children under 5, 5,990 per million peopleBurkina Faso: 19.5% of children under 5, 46.6 per million peopleBulgaria: 5.5% of children under 5, 2,401 per million peopleBahrain: 4.6% of children under 5, 849 per million peopleBosnia and Herzegovina: 7.9% of children under 5, 705 per million peopleBelarus: 1.1% of children under 5, 1,568 per million peopleBolivia: 10.7% of children under 5, 63.1 per million peopleBrazil: 8.9% of children under 5, 903 per million peopleBrunei Darussalam: 9.9% of children under 5, 506 per million peopleBhutan: 17.9% of children under 5, 236 per million peopleBotswana: 21% of children under 5, 180 per million peopleChile: 1.7% of children under 5, 707 per million peopleChina: 4.5% of children under 5, 2,107 per million peopleCongo, Dem. Rep.: 44.1% of children under 5, 10.1 per million peopleCongo, Rep.: 16.3% of children under 5, 127 per million peopleColombia: 11.6% of children under 5, 90.2 per million peopleCabo Verde: 5.3% of children under 5, 125 per million peopleCosta Rica: 10.6% of children under 5, 508 per million peopleCzechia: 2.4% of children under 5, 4,505 per million peopleGermany: 2.2% of children under 5, 5,926 per million peopleDominican Republic: 5.6% of children under 5, 20 per million peopleAlgeria: 8.9% of children under 5, 1,764 per million peopleEcuador: 17.7% of children under 5, 400 per million peopleEgypt, Arab Rep.: 12.9% of children under 5, 1,120 per million peopleEstonia: 1.3% of children under 5, 4,800 per million peopleEthiopia: 35.5% of children under 5, 89 per million peopleFinland: 1.7% of children under 5, 8,315 per million peopleUnited Kingdom: 3.5% of children under 5, 4,473 per million peopleGeorgia: 4.7% of children under 5, 1,896 per million peopleGhana: 15.6% of children under 5, 87.5 per million peopleGambia, The: 14% of children under 5, 50.9 per million peopleGreece: 2% of children under 5, 5,283 per million peopleGuatemala: 44.6% of children under 5, 1.45 per million peopleHonduras: 17.9% of children under 5, 188 per million peopleIndonesia: 22.6% of children under 5, 395 per million peopleIndia: 32.9% of children under 5, 259 per million peopleIreland: 2.2% of children under 5, 5,753 per million peopleIran, Islamic Rep.: 4.8% of children under 5, 2,240 per million peopleIraq: 9.4% of children under 5, 164 per million peopleJordan: 7.7% of children under 5, 576 per million peopleJapan: 5.2% of children under 5, 5,609 per million peopleKazakhstan: 4.4% of children under 5, 758 per million peopleKenya: 17.9% of children under 5, 384 per million peopleCambodia: 22% of children under 5, 30.4 per million peopleKorea, Rep.: 1.8% of children under 5, 9,472 per million peopleKuwait: 4.5% of children under 5, 145 per million peopleSri Lanka: 10.1% of children under 5, 94.5 per million peopleLesotho: 35% of children under 5, 32.2 per million peopleLithuania: 1.6% of children under 5, 3,704 per million peopleLatvia: 1.7% of children under 5, 2,191 per million peopleMorocco: 13.7% of children under 5, 1,083 per million peopleMoldova: 4.2% of children under 5, 650 per million peopleMadagascar: 38.4% of children under 5, 32.9 per million peopleMexico: 13.1% of children under 5, 438 per million peopleNorth Macedonia: 3.8% of children under 5, 888 per million peopleMali: 23.2% of children under 5, 26 per million peopleMalta: 3.5% of children under 5, 2,355 per million peopleMyanmar: 24.5% of children under 5, 28 per million peopleMontenegro: 8% of children under 5, 764 per million peopleMongolia: 7.1% of children under 5, 535 per million peopleMozambique: 37% of children under 5, 44.4 per million peopleMauritius: 7.8% of children under 5, 689 per million peopleMalawi: 33.2% of children under 5, 25.2 per million peopleMalaysia: 24.3% of children under 5, 1,218 per million peopleNamibia: 16.4% of children under 5, 225 per million peopleNiger: 48.3% of children under 5, 26.9 per million peopleNigeria: 33.8% of children under 5, 22.1 per million peopleNetherlands: 1.6% of children under 5, 6,563 per million peopleOman: 12.9% of children under 5, 739 per million peoplePakistan: 33.6% of children under 5, 474 per million peoplePanama: 14% of children under 5, 250 per million peoplePhilippines: 27.7% of children under 5, 320 per million peoplePapua New Guinea: 47.6% of children under 5, 33.2 per million peoplePoland: 1% of children under 5, 3,675 per million peoplePortugal: 3.2% of children under 5, 5,983 per million peopleParaguay: 3.2% of children under 5, 139 per million peopleWest Bank and Gaza: 8% of children under 5, 584 per million peopleQatar: 5.4% of children under 5, 948 per million peopleRomania: 7% of children under 5, 1,082 per million peopleRwanda: 29.8% of children under 5, 133 per million peopleSaudi Arabia: 11.1% of children under 5, 1,235 per million peopleSenegal: 17.2% of children under 5, 572 per million peopleSingapore: 2.8% of children under 5, 8,782 per million peopleEl Salvador: 9.4% of children under 5, 55.5 per million peopleSerbia: 4.6% of children under 5, 2,688 per million peopleEswatini: 18.9% of children under 5, 138 per million peopleSyrian Arab Republic: 23.5% of children under 5, 140 per million peopleChad: 31.5% of children under 5, 56.7 per million peopleTogo: 23% of children under 5, 57.8 per million peopleThailand: 12.3% of children under 5, 1,592 per million peopleTrinidad and Tobago: 7.8% of children under 5, 493 per million peopleTunisia: 8.9% of children under 5, 1,668 per million peopleTurkiye: 5.5% of children under 5, 2,645 per million peopleTanzania: 29.9% of children under 5, 19.3 per million peopleUganda: 23.5% of children under 5, 81.3 per million peopleUkraine: 11.7% of children under 5, 586 per million peopleUruguay: 6.5% of children under 5, 938 per million peopleUnited States: 4.2% of children under 5, 4,937 per million peopleUzbekistan: 6.7% of children under 5, 640 per million peopleViet Nam: 19.2% of children under 5, 836 per million peopleSouth Africa: 24.4% of children under 5, 444 per million peopleZimbabwe: 23.7% of children under 5, 95.1 per million peopleAGOBDIDOMFINKORKWTNERPRYSGP

best-fit line line after adjusting

Four ways to measure the link

MethodrpCountries
Standard (Pearson), not adjusted-0.5206.9e-9109
By rank (Spearman), not adjusted-0.7992.4e-25109
Standard (Pearson), adjusted for national income-0.0510.604109
By rank (Spearman), adjusted for national income-0.4071.3e-5109

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 109 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: +0.469 (a minus sign means it grew).

How solid is it?

Leaving out one country at a time, r ranges from -0.083 (without SGP) to -0.028 (without GTM). 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: SGP (-0.033).

Fragile: this link may not hold up.
  • 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
East Asia & Pacific15-0.19
Europe & Central Asia29-0.35
Latin America & Caribbean16-0.13
Middle East, North Africa, Afghanistan & Pakistan16-0.29
Sub-Saharan Africa29-0.22

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 third37-0.31
Middle third36-0.27
Richest third36-0.47

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
Christians62+0.04
Muslims31-0.28

By last european coloniser

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
France13-0.06
Never a European colony15-0.09
Spain16-0.14
United Kingdom32-0.01

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 = -0.251 after dropping 17 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 25years. So a link here can’t come from anything about a country that stays the same, such as its history, geography, institutions or culture.

The link also shows up within countries over time (r = +0.405). It holds even when looking only at changes from one year to the next (r = +0.137). This is the strongest kind of evidence available here: it holds when each country is compared only with itself, and it is not just a product of shared trends.

Across countries (adjusted)-0.051for comparison
Within countries-0.147each country vs itself
…and vs the same year elsewhere+0.405q = 0.000 · 80 countries
Year-on-year changes+0.137q = 0.019
Read with care.
  • Almost all of this indicator's variation is between countries, not within them, so the within-country estimate rests on a small part of the data.
  • The association is much weaker in year-on-year changes than in levels, which points to shared country-specific trends.

1,253 country-years (one country in one year), 80 countries, 2000–2024, about 16 years each on average. Share of the variation that happens within countries over time: 5% for Child stunting, 10% for Researchers. 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

0.50−0.5-100+10years Researchers trails Child stunting →lag -10: r = 0.360 (n = 805)lag -9: r = 0.376 (n = 872)lag -8: r = 0.386 (n = 927)lag -7: r = 0.404 (n = 999)lag -6: r = 0.411 (n = 1,052)lag -5: r = 0.415 (n = 1,124)lag -4: r = 0.402 (n = 1,177)lag -3: r = 0.404 (n = 1,203)lag -2: r = 0.401 (n = 1,230)lag -1: r = 0.404 (n = 1,251)lag +0: r = 0.405 (n = 1,253)lag +1: r = 0.400 (n = 1,218)lag +2: r = 0.391 (n = 1,181)lag +3: r = 0.377 (n = 1,133)lag +4: r = 0.369 (n = 1,093)lag +5: r = 0.362 (n = 1,050)lag +6: r = 0.353 (n = 999)lag +7: r = 0.342 (n = 946)lag +8: r = 0.327 (n = 888)lag +9: r = 0.312 (n = 839)lag +10: r = 0.297 (n = 780)

Same year (lag 0): +0.405. 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


% of children under 5
per million people		Years
Burundi BDI55.3%22.52024, 2018
Niger NER48.3%26.92024, 2013
Angola AGO47.7%18.92024, 2016
Papua New Guinea PNG47.6%33.22024, 2016
Guatemala GTM44.6%1.452024, 2023
Congo, Dem. Rep. COD44.1%10.12024, 2015
Madagascar MDG38.4%32.92024, 2018
Mozambique MOZ37%44.42024, 2015
Ethiopia ETH35.5%892024, 2017
Lesotho LSO35%32.22024, 2023
Nigeria NGA33.8%22.12024, 2019
Pakistan PAK33.6%4742024, 2023
Malawi MWI33.2%25.22024, 2019
India IND32.9%2592024, 2020
Chad TCD31.5%56.72024, 2016

World Bank, World Development Indicators
World Bank, World Development Indicators

Sources

Child stunting

Prevalence of stunting, height for age, modelled estimate (% of children under 5)

UNICEF, WHO and World Bank Joint Child Malnutrition Estimates · CC BY 4.0 · updated quarterly

An estimate from a statistical model. The agencies fit a model to household surveys and predict every country and year. So this is smoother than the surveys behind it, and it has values for years nobody measured. The survey-only series never reaches sixty countries in any year.

Researchers

Researchers in R&D (per million people)

UNESCO Institute for Statistics · CC BY 4.0 · updated quarterly

Researchers counted as full-time equivalents (two half-time researchers count as one), from national research surveys that many countries run only now and then. So coverage is thin outside the OECD.

How this was computed

Data used: most recent value in 2010-2025; values come from 2010–2024. 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 12,497 pairs at once, using the Benjamini–Hochberg method. Underlying data last updated DYB 2024. How the country data works · explore Child stunting and Researchers

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

More links with Child stunting or Researchers