Table 6.— Loss of precision in using total regression equations. 







Mean square 



Ratio 



Number 





Within sample 



for the total 



total 



of 



Category 



mean square 



regression 



samples 



Samples 



Georges Bank 











large haddock 



0.0072 



0.0103 



1.43 



43 



Georges Bank 











scrod haddock 



0.0070 



0.0090 



1.28 



20 



Nova Scotia 











large haddock 



0.0080 



0.0089 



1.11 



14 



Nova Scotia 











scrod haddock 



0.0065 



0.0065 



1.00 



5 



LITERATURE CITED 



Clark, John R., and Eli L. Dietsch 



1959. Length-weight tables for northwest 

 Atlantic haddock. ICNAF Sampling 

 Yearbook (2):25-37. 

 Duncan, David B. 



1955. Multiple range and multiple F tests. 

 Biometrics, 11(1): 1-42. 

 Finney, D.J. 



1946. Standard errors of yields adjusted for 

 regression on an independent measure- 

 ment. Biometrics, 2(3):53-55. 

 Grosslein, M.D. 



1962. Haddock stocks in the ICNAF Con- 

 vention Area. ICNAF Redbook 1962, 

 part 3:124-131. 

 Hennemuth, R.C., M.D. Grosslein, and F.D. 

 McCracken 



1964. Abundance, age composition of land- 

 ings, and total mortality of haddock 

 caught off southern Nova Scotia, 

 1956-1961. ICNAF Research Bull. 

 (l):43-73. 

 Kramer, Clyde Young 



1956. Extension of multiple range tests to 

 group means with unequal numbers of 

 replications. Biometrics, 

 12(3):307-310. 



Kramer, Clyde Young 



1957. Extension of multiple range tests to 

 group correlated adjusted means. Ibid. 

 13(1):13-18. 



Snedecor, George W. 



1956. Statistical methods, 5th ed., Iowa 

 State College Press, Ames, Iowa, XIII + 

 534 pp. 



