The Apportionment of Human Diversity

By the 1960s, anthropologists such as Frank B. Livingstone had concluded that "there are no races, there are only clines", a cline being a smooth gradient of genetic variation in a species across its geographic range. Lewontin's mentor Theodosius Dobzhansky challenged this, arguing that there are human discrete populations that can be distinguished by differences in the frequency of genetic traits, which he called races.[6] In an debate in the pages of Current Anthropology, Livingstone and Dobzhansky both put forward empirical data in support of their positions, but were unable to resolve the issue because ultimately the question was "much more about semantics":[6] Livingstone considered that races would be visible in "sharp discontinuities" in genetic variation, which there was no evidence of in humans; Dobzhansky instead equated races with clusters of genetic similarity, which could be found in humans.[7] The evidence available to Livingstone and Dobzhansky was mostly limited to qualitative observations of phenotypes thought to express genetic variation (e.g. skin colour),[6] but in the course of the 1960s new techniques were producing direct evidence for genetic variation in humans at a molecular level.[8] By 1972, when Dobzhansky invited Lewontin to contribute to his edited volume of Evolutionary Biology, Lewontin felt that there was sufficient data to look at the problem anew, from a "firm quantitative basis":[8]

And so I thought, ‘Well, we've got enough of this data, let's see what it tells us about the differences between human groups’. And so I just looked into the literature, and that literature was in books and so on. [...] One day I was going to give a lecture, I think it was in Carbondale, Illinois, or somewhere south. I was working in Chicago at the time. So I took a couple of these books with me and a pad of paper, and a table of logarithms which I needed for this purpose, and a little hand calculator, and I sat on this bus trip for three or four hours looking at the books, picking out the data, looking it up in the table of logarithms, doing a calculation, and writing it down in tables. And when I got back after the round trip I had all the data I needed to write the paper about how much human genetic variation there was, and so I did it.

— Richard Lewontin, in an interview in 2003.[8]

Lewontin had been interested in using quantitative methods to assess taxonomic categories for some time before 1972. Over a decade earlier, palaeontologist George Gaylord Simpson had invited him to co-author a second edition of his textbook Quantitative Zoology (1960), and Lewontin added a chapter on the analysis of variance. In it, he illustrated how this approach could be used distinguish geographically distinct races with the example of Drosophila persimilis, a species of fruit fly. Though the method was similar to that he would later apply to human genetic variation, he reached the opposite conclusion: there was much greater genetic variance between geographic populations than between individual fruit flies, so there was a reasonable basis for distinguishing taxonomic races.[8] Foreshadowing his later work on human genetic variation, he also emphasised that, because there will always be measurable differences between any two populations, it is the degree of difference compared to other axes of variation that will determine whether a grouping is biologically significant.[8] The Apportionment of Human Diversity was published in an volume dedicated to Simpson, perhaps prompting Lewontin to recall this previous work.[8]

Lewontin performed a statistical analysis of the fixation index (F_ST) in populations drawn from seven classically-defined "races" (Caucasian, African, Mongoloid, South Asian Aborigines, Amerinds, Oceanians, and Australian Aborigines). At that time, direct sequence data from the human genome was not sufficiently available, so he instead used 17 indirect markers, including blood group proteins. Lewontin found that the majority of the total genetic variation between humans (i.e., of the 0.1% of DNA that varies between individuals), 85.4%, is found within populations, 8.3% of the variation is found between populations within a "race", and only 6.3% was found to account for the racial classification. Numerous later studies have confirmed his findings.[9] Based on this analysis, Lewontin concluded, "Since such racial classification is now seen to be of virtually no genetic or taxonomic significance either, no justification can be offered for its continuance."

Many subsequent studies confirmed Lewontin's main finding.[10][11][12]

The paper was not frequently cited in the years following its publication.[2][13]

Fifty years after its publication, the paper is still frequently referenced in social media. In particular, Twitter users associated with far-right politics commonly use "Lewontin's fallacy" (referencing Edwards' 2003 critique) as a rhetorical device to dismiss scientific arguments against biological race. Commenting on the enduring significance afforded to Lewontin's paper in far-right and white nationalist discourse, geneticists Jedidiah Carlson and Kelley Harris propose that "rejection of Lewontin's interpretation has become a tenet of white nationalist ideology".[8]

• Human Genetic Diversity: Lewontin's Fallacy