8 MAL-NUTRITION AND THE TEACHER'S 



tary school often seem unaware that the same sample 

 does not pass through all the standards, at one stage there 

 is a rejection of the very dull and at another the retention 

 of the dull class. The main facts brought out are the sub- 

 stantial correlation between the teacher's estimate of general 

 capacity and examination test, and the fact that extreme 

 allowance for age and standard tends to emphasize this 

 relationship rather than to show that the teacher's estimate 

 is of little value.' Absolutely confirmatory results have 

 recently been reached by Messrs. Gilby and Waite for 

 much larger numbers. 



A considerable part of Mr. Yule's criticism is devoted 

 to a comparison of the results of the L.C.C. investigation 

 with those found in a previous investigation carried out 

 by Dr. Francis Warner^ between 1888 and 1894 in which 

 ioo,cco children were examined. There has thus been 

 forced upon the present writer the unpleasant duty of 

 criticizing in detail an investigation carried out nearly 

 twenty years ago, a duty which he would have been glad to 

 have been spared. Mr. Yule has himself already published 

 a very extensive analysis of Dr. Warner's material in his 

 paper * On the Association of Attributes in Statistics ' ^ ; 

 it is very unfortunate that Mr. Yule not only made no 

 attempt to estimate the value of the material on which he 

 expended so much energy, but that he laboured under the 

 additional disadvantage of using a ' coefficient of associa- 

 tion ' which he now admits cannot be compared with the 

 correlation coefficient.^ How widely these coefficients of 



1 Report on the Scientific Study on the Mental and Physical Conditions of 

 Childhood. Published by the Committee, Parkes Museum. London, 1895. 



Journal of the Royal Statistical Society, vol. Ivi, p. 71, and vol. lix, p. 125. 

 British Medical Journal^ July 27, 1889, p. 187. Report of the British Asso- 

 ciation for the Advancement of Science, 1893, p. 614, &c. 



2 Phil. Trans. Royal Society, A. 238, 1900, pp. 257-319. 



3 In Mr. Yule's paper, the association coefficient was used as if it were 



