PROFESSOK PEARSON S CONTRIBUTIONS TO OSTEOLOGY. 



468 



statistics, whether relative or absolute measurements of organs, 

 the frequency curves all deviate from the normal curve — how- 

 ever slight the deviation — in the direction of Type IV." 



Now this curve corresponds to a hypergeometrical, and 

 not to a binomial series, and consequently affords " evidence 

 against the usual hypothesis that in biological matters the 

 chances of deviation on either side of the mean are equal, 

 and the ' contributory causes ' independent and indefinitely 

 great in number." As an example of Type IV. the length- 

 breadth index of 900 Bavarian skulls is worked out. 



The general form of the curve of Type IV. is shown below 



(fig- 4). 



It is skew! and unlimited in either direction. 



Fig. 4. 



Variation, Correlation, etc. — In the next paper of the series 

 in the Philosophical Transactions, viz, " Regression, Heredity, 

 and Panmixia," Professor Pearson discusses the mathematical 

 treatment of these phenomena. The memoir begins, how- 

 ever, with a very useful series of definitions, namely, 

 of variation, correlation, natural selection, sexual selection, 

 reproductive selection, heredity, regression, and panmixia. 

 For our present purposes we will confine ourselves to a brief 

 consideration of four of the above. 



(1) Variation.- — Professor Pearson says, "If a curve be con- 

 structed of which the ordinate y is such that ySx measures 

 the frequency with which an organ lying in size between 

 X and x + Sx occurs in a considerable population (500 to 

 1000 or more), the constants which for any particular organ 



