382 



BELL SYSTEM TECHNICAL JOURNAL 



5 . Conclusion 



Based upon evidence such as already presented, it appears to be 

 practicable to set up criteria by which to determine when assignable 

 causes of variations in quality have been eliminated so that the product 

 may then be considered to be controlled within limits. This state of 

 control appears to be, in general, a kind of limit to which we may expect 

 to go economically in finding and removing causes of variability without 

 changing a major portion of the manufacturing process as, for example, 

 would be involved in the substitution of new materials or designs. 



III. Advantages Secured through Control 



1. Reduction in the Cost of Inspection 

 If we can be assured that something we use is produced under con- 

 trolled conditions, we do not feel the need for inspecting it as much as 



fi,6 





A S O N 

 1927 



M J J / 



1928 

 MONTHS 



S O N D J F 



MAM 

 1929 



0.6 



<-0,2 



_1_ 



_!_ 



JASON 

 1927 



_1_ 



_1_ 



J_ 



_1_ 



_1_ 



_1_ 



MAMJ JASON 

 1926 

 MONTHS 



F M A M 

 1929 



Fig. 11 — Approach to stable equilibrium or control as assignable causes are weeded 

 out, thus reducing the need for inspection. 



we would if we did not have this assurance. For example, we do not 

 waste our money on doctors' bills so long as we are willing to attribute 

 the variability in our health to the effects of what in our present termin- 

 ology corresponds to a constant system of chance causes. 



In the early stages of production there are usually causes of varia- 

 bility which must be weeded out through the process of inspection. As 



