6) An expert criminalist and a recent trainee both participate in a quality assurance exercise for certification by ASCLD/LAB. They are given a standard sample of alcohol in water at a nominal stated concentration of 15.0000 ppt. Both measure the concentration using 10 replicates with the following results. Run # Expert Trainee Analysis Quality Assurance Test 1 13.50 14.25 18.00 17.00 2 13.96 14.46 16.00 3 13.16 12.98 15.00 Concentration 14.00 4 13.88 13.50 13.00 5 14.24 13.32 12.00 11.00 6 13.95 14.87 10.00 0 2 10 12 7 14.16 13.91 Sample Number 8 14.45 15.10 9 13.81 17.17 10 14.03 14.38 Avg 13.91 14.39 Std Dev 0.37 1.18 Reference Tables: Table of critical values of N Qcrit(90%) Qcrit(95%) Qcrit(99%) 3 0.941 0.970 0.994 4 0.765 0.829 0.926 5 0.642 0.710 0.821 6 0.560 0.625 0.740 7 0.507 0.568 0.680 8 0.468 0.526 0.634 9 0.437 0.493 0.598 10 0.412 0.466 0.568 Table of Ciritical Values of Student-t df 90% 95% 99% 1 6.31 12.7 63.7 2 2.92 4.3 9.92 3 2.35 3.18 5.84 4 2.13 2.78 4.6 5 2.02 2.57 4.03 6 1.94 2.45 3.71 7 1.9 2.36 3.5 8 1.86 2.31 3.36 9 1.83 2.26 3.25 10 1.81 2.23 3.17 Infinity 1.64 1.96 2.58 a) Use Dixon's Q test to see if the trainee's maximum data point should be excluded at 95% confidence limits. b) Report the 95% confidence limits of the mean for both the expert and the trainee (with the modified trainee data set, if you found an outlier in part a). e) Assuming negligible error in the stated standard concentration (i.e., 15.0000 is exact), is there a significant difference for the trainee's average relative to the stated standard at 95% C.L.? d) Assuming negligible error in the stated standard concentration, is there a significant difference for the expert's average relative to the stated standard at 95% C.L.? e) A second expert also makes 10 measurements and obtains an average of 14.55 with a standard deviation of 0.37. Calculate the difference and the 95% confidence limits on the difference between the two experts' averages. Is there a significant difference at 95% C.L. (leading one to be suspicious of the first expert's methods)