Downloaded from https://www.everyspec.com -N MIN1 TABLE 2-26 SAMIE SiZS REQUIRED TO DETECT PRESCRIBED DIPFIREUCUS SWEMEN AVERAGES WHEN THE $I1N'OP THE DIFFERENCE IS NOT IMPORTANT"6 The table entry is the sample size (N,) required to detect, with probability 1 -0, that the average mt of a new product differs from the standard mo (or that two product averages M, and me differ). The standardized difference is d, where d. (or d 1- A if we amcompring two products). v + 'd ; The standard deviations are assumed to be 'known, and N is determined by the formnula:
IV :1 a .01 - - - Ii i I -I ) I .so .60 .70 .O .90 .95 .99 664 801 962 1168 1488 1782 2404 .2 166 201 241 292 372 446 601 .4 42 61 61 73 93 112 151 .6 19 23 27 83 42 50 67 11 13 16 19 24 28 38 1.0 7 9 10 12 15 18 25 1.2 5 6 7 9 11 13 17 1.4 4 5 5 6 8 10 18 1.6 3 4 4 5 6 7 10 1.4 3 3 8 4 5 6 8 2.0 2 3 a 34 4 6 7 3.0 1 1 2 '.2 2 3 if we must estimate, from our sample and ube Student a I, then wcjhould add 4 to the tabulated values to obtain the epproximate required sample size. (If we are comparing two product averageo, add 2 to the tabulated values, to obtain the required slie of oen sample.
For this cae, we must have #A - a - .05 .50 .60 .0 .2 0 .93 .99 .1 885 490 618 785 1051 1300 1838 .2 97 123 155 197 263 325 460 .4 25 31 39 50 66 82 115 .6 1 1 14 18 22 30 87 52 .8 7 8 10 13 17 21 29 1.0 4 5 7 8 11 13 19 1.2 3 4 5 6 8 10 13 1.4 2 3 4 5 6 7 10 1.6 2 2 3 4 5 6 8 1.1 2 2 2 3 4 5 6 2.0 1 2 2 2 3 4 6 I.0 1 1 I 1 2 2 3 If we rnMIt estimate v from our armple and ume Student f, thon we should add 2 to the tabulated values to obtain the approximate required sample siize. (If We are eompi,rinx two product avev'agiem, add I to the tabulaned values to obtain the required size of each sample. For this eame, we mus•t have W, - *.).