464 
SIR. B. C. BRODIE ON THE ACTION OF ELECTRICITY ON GASES. 
of which give 2* 37 as the value of It. It might be thought at first sight that these expe- 
riments should be rejected, as affected by some special source of error ; but, on the other 
hand, there is one value of It in the Table which exhibits a nearly equal divergence from 
the mean in the other direction, namely 1*7, experiment 26 : also if we reject on these 
grounds the number 2*37, no adequate reason can be given for retaining such a number as 
2'24; and I find, on turning to my note-book, that experiments 7, 17, 18, 8 were made 
successively on the same day, by the same method, under the same conditions, and by the 
same observer in the order of the preceding numbers, the value of 11 in the several 
experiments being (7) 2*37, (17) 1*96, (18) 2*00, (8) 2*37 ; and I cannot but attribute the 
divergence of these numbers from the mean to an accidental accumulation of errors in 
one direction. 
In column I. of the following Table is given the value of II in each of the thirty-three 
experiments referred to ; column II. contains the differences of these values from the 
mean value of It, and column III. the squares of the differences. 
Experiments with Hydriodic Acid. 
I. 
R=— . 
T 
II. 
Difference from 
the mean. 
III. 
Squares of the 
differences. 
1-89 
-•1 
•01 
1*89 
-•1 
•01 
1-98 
-•01 
•0001 
1-96 
-•03 
•0009 
2*24 
+ •25 
•0625 
2’20 
+ •21 
•0441 
2-37 
+ •38 
-1444 
2*37 
+ •38 
•1444 
1-83 
-•16 
•0256 
2-03 
+ •04 
•0016 
2-11 
+ •12 
•0144 
2-05 
+ •06 
•0036 
1-84 
-•15 
•0225 
1-88 
-•11 
•0121 
1-87 
-•12 
•0144 
2-15 
+ •16 
•0256 
1-96 
-•03 
•0009 
2-00 
+ •01 
•0001 
2*20 
+ •21 
•0441 
2-00 
+ •01 
•0001 
1-91 
-•08 
•0064 
1*77 
*22 
•0484 
2-13 
+ •14 
•0256 
2-03 
+ •06 
•0036 
1-81 
— •18 
•0324 
1-70 
-•29 
•0841 
2‘02 
+ •03 
•0009 
2-00 
+ •01 
•0001 
2-03 
+ •04 
•0016 
1-82 
-•17 
•0289 
1-84 
-•15 
•0225 
1-88 
— •11 
•0121 
1-88 
-•11 
•0121 
Mean =1*99 cub. centim. 
Sum~8601 
