posted by Janice on .
Miller (2008) examined the energy drink consumption of college undergraduates and found that males use energy drinks significantly more often than females. To further investigate this phenomenon, suppose a researcher selects a random sample of n=36 male undergraduates and a sample of n=25 females. On average, the males reported consuming M=2.45 drink per month and females had an average of M=1.28. Assume that the overall level of consumption for college undergraduates averages population mean=1.85 energy drinks per month, and that the distribution of montly consumption scores is approximately normal with a standard deviation of 1.2.
a) Did this sample of males consume significantly more energy drinks than the overall population average? Use a one-tailed test with a a=.01
b) Did this sample of females consume significantly fewer energy drinks than the overall population average? Use a one-tailed test with a a=.01
Z = (mean1 - mean2)/standard error (SE) of difference between means
SEdiff = √(SEmean1^2 + SEmean2^2)
SEm = SD/√n
If only one SD is provided, you can use just that to determine SEdiff.
Find table in the back of your statistics text labeled something like "areas under normal distribution" to find the proportion/probability for each Z score.