EX16-11.txt Exercise 16.19 from Howell's fundamentals text, page 333. Do note that there is a data error in the text book. The next to last score in the nonsmokers data should be a 19, not a 16. I entered the data in stacked fashion, with group 1 being nonsmokers, group 2 delayed smokers, and group 3 active smokers. ------------------------------------------------------------------ MTB > retr 'ex16-19' MTB > info COLUMN NAME COUNT C1 group 45 C2 recall 45 MTB > onew c2 c1; SUBC> fisher. ANALYSIS OF VARIANCE ON recall SOURCE DF SS MS F p group 2 2643 1322 4.74 0.014 ERROR 42 11700 279 TOTAL 44 14344 INDIVIDUAL 95 PCT CI'S FOR MEAN BASED ON POOLED STDEV LEVEL N MEAN STDEV ----------+---------+---------+------ 1 15 28.87 14.69 (--------*--------) 2 15 39.93 20.13 (--------*--------) 3 15 47.53 14.65 (--------*-------) ----------+---------+---------+------ POOLED STDEV = 16.69 30 40 50 FISHER'S multiple comparison procedure Nominal level = 0.0500 Family error rate = 0.120 Individual error rate = 0.0500 Critical value = 2.018 Intervals for (mean of column group) - (mean of row group) 1 2 2 -23.37 1.23 3 -30.97 -19.90 -6.37 4.70 -------------------------------------------------------------------- The active smokers recalled significantly more propositions than did the nonsmokers.