Karl Pearson and Egon S. Pearson 
141 
Having obtained (jIss'/'^w')" -md for the trial values of r, it is only a matter 
of adding Vsg/inss'/nsn'}^ f<^i' values of s and s' on the machine in order to obtain : 
The values obtained were : 
0-45 
0-50 
0-55 
u — 
+ -157,074 
+ -012,276 
- -209,976 
Whence by inverse interpolation* we find : 
v = 0 for r,, = -5084, 
which is "polychoric r" as based upon Equation (xvii). We shall compare later 
the vahie for ?■ as found by other processes. But the above value is clearly well 
in accord with the usual result for paternal correlation in man. 
Table V gives the working values of Pss'/i^ss'/^ss'T- 
TABLE V. Valiiesofvss'Knss'lnss'Tf- 
s' 
r 
s = l 
s = 2 
8 = 3 
s=.4 
s = 5 
s = 6 
s = 7 
1 
(«) 
(b) 
(0) 
+ -007,186 
+ 006,010 
+ •005,071 
+ -014,435 
+ -009,972 
+ -005,331 
- ^022,001 
- •osijgsB 
- ^049,232 
0 
0 
0 
- -018,159 
- -030,424 
- -050,132 
0 
0 
0 
0 
0 
0 
2 
(a) 
(0) 
+ ■018,405 
+ -013,851 
+ -009,274 
+ •141,463 
+ •140,141 
+ ^139,495 
- •006,688 
- •010,202 
- ^014,930 
- ^021,475 
- •027,086 
- ^035,275 
- -013,436 
- -018,162 
- -025,871 
- •011,685 
- •Ol 6,986 
- ^026,399 
0 
0 
0 
3 
{a) 
(c) 
-•021,876 
- -031,462 
- -047,779 
+ •001,794 
+ ^000,032 
- ^002,425 
+ ^034,007 
+ •038,425 
+ ^042,934 
+ -020,301 
+ ^022,755 
+ •025,189 
- -005,265 
- -007,060 
- -009,544 
- ^024, 509 
- ^032,660 
- ^044,832 
- •002,816 
- •004,166 
- -006,579 
4 
(«) 
{b) 
(c) 
- -002,890 
- -004,543 
- -007,695 
-•024,189 
- -030,027 
- -038,318 
+ •Oil, 556 
+ •013,001) 
+ •014,488 
+ ^029,810 
+ ^031,921 
+ ^034,0 10 
+ -010,036 
+ -010,316 
+ -010,608 
+ ^002, 968 
+ ^002,231 
+ ^001,398 
- -010,247 
- '015,487 
- -023,039 
5 
(«) 
(b) 
(c) 
0 
0 
0 
- -030,326 
- -039,760 
- -054,439 
- •000,360 
- ^001,075 
- •002,126 
+ ^019,498 
+ ^020,230 
+ ^020,981 
- -010,803 
+ -010,914 
+ •011,058 
+ •017,610 
+ •016,869 
+ •016,285 
+ ^000,491 
- ^001,027 
- ^002,916 
6 
(a) 
(b) 
(c) 
0 
0 
0 
- -020,008 
- -028,474 
- -043,219 
- ^022,838 
- ^030,341 
- •041,234 
+ -007,545 
+ -007,029 
+ -006,516 
+ -004,686 
+ '004,542 
+ '004,433 
+ '059,958 
+ '0.56,264 
+ •053', 151 
+ •012,415 
+ •010,41] 
+ -008,654 
7 
(a) 
(b) 
ic) 
0 
0 
0 
- -017,910 
- -028,491 
- -047,576 
- ^030,574 
- ^044,067 
- •067,356 
- -002,307 
- -003,750 
- -005,755 
+ ^003,984 
+ ^002,606 
+ •001,135 
+ •014,:391 
+ •012,497 
+ ^010,895 
+ -023,291 
+ -019,449 
+ -016,389 
^ (a) = -(-•157,074, ;S' (6)= +-012,276, (c) =- -209,976. 
* The formula used was Casus I or x^ = 5|, + |^ (Ar_i + Azu) + 2^-5%oi the solution of tlie quadratic 
giving 6. 
•f The table suggests, a posteriori, that we should have got quite reasonable results from linear inter- 
polation ; we have : from (a) and (/)) )- = -5042 ; from («) and (c) r=-49'28, and from (h) and (c) r = ^5025, 
as against our '5034. It should be noticed that the values in Table V are not always in agreement in 
the last figure with those obtained by dividing Vg^, in Table IV by the {ns.rlihs')' of that table, because the 
somewhat more accurate process was adopted of multiplying by v^ss' and then dividing by n-g,,. . Still 
the physical meanings of and {iiss'l":<s')' are so prominent in the work that it seemed desirable 
to register their values. 
