analysis of variance for each station. The between-years sum of squares 



N N 



is y (/So -^o)^; the within-years sum of squares is y a^^. The quantities 

 1 1 



^0 and CT£)2 are individual year values and the summations are over the N years 

 in a sample. Since the off-diagonal terms in the product-moment matrix are 

 negligible, an individual year oq^ divided by the appropriate sample size is an 

 estimate of the variance of /So for that year. (A discussion of the variance of 

 regression coefficients can be found in reference 11.) The F-ratios are all highly 

 significant, and it is concluded that there are real year-to-year differences in the 

 /So's. 



TABLE 7. ANALYSIS OF VARIANCE OF ANNUAL ;S„ 



Location 



Between Years 



Within Years 



F-Ratio 







6 







s 













o 







o 













-a 







-o 













0) 







OJ 











CB 



OJ 





CO 



0) 













^ 

















t; 



tlH 



cu 





[i< 



S 









a* 



o 



CO 



3 



5* 



•o 



CO 

 3 











cc 



a* 





cc 



a" 











<D 



en 



t*H 



a> 



CO 









o 



0) 





o 













g 



En 



CO 



e 



feb 



CO 





s 







cu 



01 





w 











CO 



Q 



S 



c» 



Q 



S 



b. 



Cl. 



PAPA 



0.912 



6 



0.1520 



1.399 



1560 



0.00090 



169 



2.8 



ECHO 



1.338 



6 



0.2230 



2.691 



1498 



0.00180 



124 



2.8 



Cape St. James 



3.490 



20 



0.1745 



9.434 



6075 



0.00155 



113 



1.9 



Triple Island 



6.393 



20 



0.3197 



9.016 



7159 



0.00126 



254 



1.9 



Langara Island 



3.435 



19 



0.1808 



12.111 



6302 



0.00192 



94 



1.9 



Scripps Pier 



14.659 



39 



0.3759 



35.255 



14152 



0.00249 



151 



1.6 



Similar analyses of randomness have been applied to the Scripps Pier 

 40-year time-series of annual amplitude, annual phase, and percent variance 

 explained. Histograms are shown in figures 7B, C, and D. In all cases the histo- 

 grams are typical of those obtained from a sample of size 40 fi"om a population 

 where the variable in question has a unimodal, slightly skewed frequency func- 

 tion. In addition the run tests for trend yield total runs of 18, 23, and 22 for 

 amplitude, phase, and percent variance explained, respectively. All these totals 

 are greater than the still applicable critical value of 15 used for the /8o's, so 

 again it is concluded that no trend exists in the time-series of these variables. 



26 



