b.) Specify the p -value for this test result.

c.) If appropriate (because the test result is statistically signifi cant), use Cohen’s d to estimate theeffect size.

d.) How might this test result be reported in the literature?

15.8 A school psychologist wishes to determine whether a new anti smoking fi lm actually reduces the daily consumption of cigarettes by teenage smokers. The mean daily cigarette consumption is calculated for each of eight teen-age smokers during the month before and the month after the fi lm presentation, with the following results: (table)a.) Using t , test the null hypothesis at the .05 level of signifi cance.

b.) Specify the p -value for this test result.

c.)If appropriate (because the null hypothesis was rejected), construct a 95 percent confi dence interval for the true population mean for all difference scores, and use Cohen’s d to obtain a standardized estimate of the effect size. Interpret these results.

15.10 In a classic study, which predates the existence of the EPO drug, Melvin Williams of Old Dominion University actually injected extra oxygen-bearing red cells into the subject's’ bloodstream just prior to a treadmill test. Twelve long-distance runners were tested in 5-mile runson treadmills. Essentially, two running times were obtained for each athlete, once in the treatment or blood-doped condition after the injection of two pints of blood and once in the placebo control or non-blood-doped condition after the injection of a comparable amount of a harmless red saline solution. The presentation of the treatment and control conditions was counterbalanced, with half of the subjects unknowingly receiving the treatment fi rst, then the control, and the other half receiving the conditions in reverse order. Since the difference scores, as reported in the New York Times, on May 4, 1980, are calculated by subtracting blood-doped running times from control running times, a positive mean difference signifi es that the treatment has a facilitative effect, that is, the athletes’ running times are shorter when blood doped. The 12 athletes had a mean difference running time, D, of 51.33 seconds with a standard deviation, s D , of 66.33 seconds.a.) Test the null hypothesis at the .05 level of significance.