434 
PROFESSOR K. PEARSON AND MISS A. LEE ON THE DISTRIBUTION 
Table III. contains the values of the mean and the moments calculated directly 
from the observed frequencies. In determining the moments, the observation 
polygons were regarded as trapezia (‘Phil. Trans.,’ A, vol. 153, p. 350). Table IV. 
then gives the constants of the theoretical distribution and the physical constants of 
the frequency deduced from them. The constants ijo, p, y and the mean M, suffice to 
determine the form of the frequency distribution. But any other three constants 
would serve equally wmll. Thus, we might take the three physical constants, yg the 
frequency of the modal height, cr the variation, and Sk. the skewness of the distri¬ 
bution. Or. we might use frequency ot the mean instead of the frequency of 
the mode. In a memoir, which one of us hopes to shortly publish,"' the probable errors 
are worked out for the constants of any frequency curve, and it is shown that these 
errors are not, as in the case of a normal frequency distribution, uncorrelated. An 
error, for example, in y, marks a correlated error in and in the mean, while in the 
case of the normal frequency curve there is no correlation between its position (mean) 
and shape (standard deviation). It becomes accordingly of considerable importance 
to determine which are the quantities in barometric frequency which have the least 
percentage probable errors, and then to adopt these as our standard constants of 
barometric frequency. 
Table III. (The unit of is iV-) 
j 
Station. 
M,. 
1 
! 
^St. Leonards .... 
29''9834 
Southampton .... 
29-9814 
. 
1 iH 
Babbacombe .... 
29-9787 
t ri 
Carmarthen. 
29-9518 
o 
Chnrchstoke .... 
29-9545 
' ^ 
Llandudno . 
29-9229 
o 
' s 
Parsonstown .... 
29-9271 
1 cc 
Markree Castle.... 
29-8861 
: ^ 
Armagh. 
29-9134 
! 
' ^ < 
O h 
Londonderry .... 
29-8905 
Stonyhurst. 
29-9406 
Scaleby. 
29-8862 
o 
• 1—1 
-+5 
Glasgow . . . 
29-8859 
1 
Lan dale. 
29-8570 
Dunrobin Castle . 
29-8457 
! S 
Dundee. 
29-8695 
i O 
O 
Scarborough .... 
29-9028 
i ® 
i OD 
I 
Hillington. 
29-94-29 
Geldeston. 
29-9476 
1 
1 
1 
^Margate. 
29-9745 
! ■ 
r 
Dover-Dnngeness . 
29-9558 
London . 
29-9660 
C_J “ 
Ca mbridge. 
29-9524 
/‘2- 
/'s- 
/'4- 
10-1350 
8-6111 
312-4840 
10-8126 
12-4493 
393-4473 
10-901-2 
13-0321 
397-0938 
12-0724 
14-8749 
475-8197 
12-664-2 
15-9835 
511-4453 
13-0338 
13-6743 
529-1235 
13-1640 
18-6-224 
560-2627 
15-4049 
24-4703 
707-7482 
13-7001 
22-7935 
622-332-2 
14-7902 
20-6538 
666-3570 
12-2702 
13-8613 
515-0601 
14-0539 
20-4879 
617-9683 
14-3712 
•23-2779 
663-3914 
150354 
27-3287 
72-2-9168 
14-3639 
2-2-2559 
652-1105 
14-7373 
23-9262 
701-9974 
12-9644 
17-1137 
555-0735 
11-7452 
15-0299 
450-6021 
11-1784 
12-7585 
409-7187 
10-3937 
15-5596 
378-2518 
10-3496 
10-7772 
10-8159 
11-1621 
— 
11-4491 
13-3671 
— 
* See Peakson and Filon, “On the Probable Errors of Frequency Constants.” (Abstract) ‘Roy 
.Soc. Proc.,’ vol. 62, p. 173. 
