No. 3] VARIATION IN THE TEETH OF NEREIS. 135 



The fact that by dropping one individual from a series a 

 curve may be thrown from Type IV to Type I and may be 

 made to fit equally well in either case, raises a serious ques- 

 tion as to the biological importance of the distinction between 

 Pearson's Type I and Type IV. Pearson ('95) himself says : 

 " It seems very possible that discreteness rather than continu- 

 ity is characteristic of the ultimate elements of variation ; in 

 other words, if we replaced the curve by a discrete series of 

 points, we should find a limited range. It is the analytical 

 transition from this series to a closely fitting curve which 

 replaces the limited by an unlimited range. Exactly the same 

 transition occurs when we pass from symmetrical point bino- 

 mial to normal curve. Thus while Type I marks an absolutely 

 limited range, Type IV does not necessarily mean that the 

 range is actually unlimited." 



It appears from the results obtained in the two calculations 

 given above that even less value can be placed upon any dis- 

 tinction between Type I and Type IV than is suggested by 

 Pearson. The difference of one individual actually causes, 

 here, the transition from one type to the other, the individual 

 being at the extreme of the series. 



3. Correlation. 



In the table on the following page every possible combina- 

 tion of teeth for the two sides is given, together with the actual 

 number of specimens for each combination of definite, indefinite, 

 and total teeth. 



From this series of combinations the following results were 

 obtained for the coefficient of correlation. The calculations 

 were made by Pearson's method and checked by the briefer 

 method of Duncker. 



Correlation between Right and Left Definite Teeth, r = + o.688o.oi36 



" " Indefinite " r= + 0.725 0.01 21 



" " ' " " Total " r= + o.82oo.oo8i 



" Right Definite and Left Indefinite, r - - o.424o.o23i 



Bearing in mind that an index of i signifies a perfect corre- 

 lation, and that o indicates an entire lack of it, we see that the 



