Table 8.1. Galton's 1885 cross-tabulation of 928 adult children born of 205 midparents, by their height and their midparent's height. Height of Total Total the mid-parent no. of no. of in inches Height of the adult child adult mid- children parents Medians <61.7 62 63 64 65 66 67 68 69 70 71 72 73 >73.7 .2 .2 .2 .2 .2 .2 .2 .2 .2 .2 .2 .2 >73.0 ‹ ‹ ‹ ‹ ‹ ‹ ‹ ‹ ‹ ‹ ‹ 1 3 ‹ 4 5 ‹ 72.5 ‹ ‹ ‹ ‹ ‹ ‹ ‹ 1 2 1 2 7 2 4 19 6 72.2 71.5 ‹ ‹ ‹ ‹ 1 3 4 3 5 10 4 9 2 2 43 11 69.9 70.5 1 ‹ 1 ‹ 1 1 3 12 18 14 7 4 3 3 68 22 69.5 69.5 ‹ ‹ 1 16 4 17 27 20 33 25 20 11 4 5 183 41 68.9 68.5 1 ‹ 7 11 16 25 31 34 48 21 18 4 3 ‹ 219 49 68.2 67.5 ‹ 3 5 14 15 36 38 28 38 19 11 4 ‹ ‹ 211 33 67.6 66.5 ‹ 3 3 5 2 17 17 14 13 4 ‹ ‹ ‹ ‹ 78 20 67.2 65.5 1 ‹ 9 5 7 11 11 7 7 5 2 1 ‹ ‹ 66 12 66.7 64.5 1 1 4 4 1 5 5 ‹ 2 ‹ ‹ ‹ ‹ ‹ 23 5 65.8 <64.0 1 ‹ 2 4 1 2 2 1 1 ‹ ‹ ‹ ‹ ‹ 14 1 ‹ Totals 5 7 32 59 48 117 138 120 167 99 64 41 17 14 928 205 Medians - - 66 67 67 67 67 68 68 69 69 70 - - - - - .3 .8 .9 .7 .9 .3 .5 .0 .0 .0 Source: Galton (1886a). Note: All female heights were multiplied by 1.08 before tabulation. Galton added an explanatory footnote to the table: "In calculating the Medians, the entries have been taken as referring to the middle of the squares in which they stand. The reason why the headings run 62.2, 63.2, &c., instead of 62.5, 63.5, &c., is that the observations are unequally distributed between 62 and 63, 63 and 64, &c., there being a strong bias in favour of integral inches. After careful consideration, I concluded that the headings, as adopted, best satisfied the conditions. This inequality was not apparent in the case of the Mid-parents." Galton republished these data in 1889, where they are referred to as the R.F.F. Data (Record of Family Faculties); he then noted that the first row must be in error (four children cannot have five sets of parents), but he claimed that "the bottom line, which looks suspicious, is correct" (p. 208). Source: p. 286 of Stigler, S. The history of statistics Belknap Press of Harvard Univ. Press, 1986.