I o DAREISHIRE, Tables illustrating Statistical Correlation. 



numbers at the left-hand end of (but beyond) the rows 

 have the same signification, except that they refer to 

 first throws. 



At the base of (but below) most of the columns are 

 numbers, which signify the number of times the event, 

 indicated by the figure at the top of the column, happened 

 in the 500 second throws. For example, a 2 occurred 12 

 times ; a 3, 25 times ; a 4, 51 times ; and so on. At the 

 right hand end of (but beyond) most of the rows are 

 numbers which signify the number of times the event 

 indicated by the figure at the left of the row happened in 

 the 500 first throws. For example, a I occurred 3 times ; 

 a 2, 8 times ; a 3, 24 times ; and so on. 



So far, we have only referred to the figures outside 

 the table, and I hope I have made clear to you what 

 they mean. Now, we must turn our attention to the 

 table itself. It will be found that the numbers at the 

 bases of the columns are the sums of the numbers in the 

 columns above them ; and that the numbers at the right- 

 hand ends of the rows are the sums of the numbers in the 

 rows to the left of them. Each column intersects all the 

 rows, and each row intersects all the columns of the table. 

 Every square is part both of a column and of a row. 



What is the meaning of the numbers in the squares? 

 The figure in any square gives the number of times the 

 result indicated by the number at the left-hand end of the 

 row of which it is a part happened in a first throw, and 

 was followed by the result indicated by the number at 

 the top of the column of which it is a part, in the second 

 throw. For example, starting with the top row we see 

 that there was not a single case of a thrown at all in 

 these 500 pairs of throws. Coming to the second row we 

 see that there was one case of a 1 in a first throw followed 

 by a 2 in the second ; one of a 1 in a first followed by a 



