326 STATISTICAL STUDY OF INHERITANCE 



(Grammar of Science, 1900, p. 479). Elsewhere he says.: " The 

 law of ancestral heredity is likely to prove one of the most brilliant 

 of Mr. Galton's discoveries ; it is highly probable that it is the 

 simple descriptive statement which brings into a single focus all 

 the complex lines of hereditary influence. If Darwinian evolution 

 be natural selection combined with heredity, then the single 

 statement which embraces the whole field of heredity must 

 prove almost as epoch-making to the biologist as the law of 

 gravitation to the astronomer." 



Prof. Karl Pearson has himself given a statement of the law of 

 ancestral inheritance somewhat different from Galton's, but his 

 methods and general results are practically the same. The 

 following quotation (i9O3a, p. 215) is useful : 



" Taking our stand, then, on the observed fact that a know- 

 ledge neither of parents nor of the whole ancestry will enable 

 us to predict with certainty in a variety of important cases the 

 character of the individual offspring, we ask : What is the correct 

 method of dealing with the problem of heredity in such cases ? 

 The causes A, B, C, D, E, . . . which we have as yet succeeded 

 in isolating and denning are not always followed by the effect 

 X, but by any one of the effects U, V, W, X, Y. We are, there- 

 fore, not dealing with causation but correlation, and there is, 

 therefore, only one method of procedure possible ; we must 

 collect statistics of the frequency with which U, V, W, X, Y, Z, 

 respectively follow on A, B, C, D, E. . . . From these statistics 

 we know the most probable result of the causes A, B, C, D, E, 

 and the frequency of each deviation from this most probable 

 result. The recognition that in the existing state of our know- 

 ledge the true method of approaching the problem of heredity 

 is from the statistical side, and that the most that we can hope 

 at present to do is to give the probable character of the offspring 

 of a given ancestry, is one of the great services of Francis Galton 

 to biometry." 



Pearson has worked out the average correlation between off- 



