CONTRIBUTIONS TO THE THEORY OF EVOLUTION. 
451 
Whence we deduce to determine qi and '• 
1 — SY; + 473 
73 - 73 
(Zl + <l2 — 
73(1 + 73)(73 - 1 - 273) 
(273- 73 + 7373) (73-73) 
. (xxix.), 
and the solution proceeds as before. 
(6.) IllusU'ations .—I propose to note a few distributions of frequency in wiiich I 
have come across Types V. and VI. 
(A.) Statistics oj Age of Bride at Marriage, the Bridegroom s Age heing bet ween 
24 and 25 years.'^ 
The observations given in the table, p. 454, are taken from Perozzo’s memoir : 
“ Nuove Applicazioni del Calcolo delle Probabilita . . . ‘ lleale Accademia dei 
Lincei,’ Anno CCLXXIX., 1881-2, Tavola 1. 
The total number of recorded marriages is 28,454. The moments were calculated 
by using Sheppard’s corrections (‘ London Math. Soc. Proc.,’ vol. 29, p. 369), and are 
as follows :— 
Mean age of bride = 22'1877. 
IX, — 13-3346 
/X3 = 67'8145 
= 1224-6342 
Whence : (Bi = 1-9396 
/33= 6-8873 
Ki = 1-9558 
K,= 1-1094 
Thus by p. 445 we see that Type VI, is the frequency curve to be selected, ljut as 
K, does not differ widely from unity, we sliall probably get a good fit from Type V. 
as well. 
Taking Type VI. first, we find : 
7- = - 12-11075, e = - 317-84987. 
The quadratic (xxiii.) is accordingly : 
2^ + 12-11075 2 — 317-84987 = 0. 
* 1 selected this example at random, as one out of several leading to the curve types it was my 
object to illustrate. There is so much tampering with statistics, however, whenever they refer to the ages 
of women, that it would probably have been better to have used the men. 
3 M 2 
