statistics

1.       When is it appropriate to use the one-sample Z test?

2.       What’s with the z in Z test?  What similarity does it have to a simple z or standard score?

3.       For the following situations, write out in words a research hypothesis.

A.      Bob wants to know if the weight loss for his group on the chocolate-only diet is a representative of weight loss in a large population of middle-aged men.

B.      The health department is charges with finding out if the rate of flu per thousand citizens for this past flu season is comparable to the average rate of the past 50 seasons.

C.      Blair is almost sure that his monthly costs for the past year are not representative of his average monthly cost over the past 20 years.

4.       Flu cases this past flu season in the Oshkosh school system were about 15 per week.  For the entire state, the weekly average is 16 and the standard deviation, 2.35.  Are the kids in Oshkosh as sick as the kids throughout the state?

Chapter 11

3. Time for some tedious by hand practice just to see if you can get the numbers right.  Using the following information, calculate the t-test statistic by hand.

a. _¯x1=62   x2=60   n1=10  n2=10  s2/1=6  s 2/2=10

b. x1=158   x2=157.4   n1=22   n2=26   s 2/1=4.23   s 2/2=6.73

c. x1=200   x2= 198   n1=17   s 2/1=6   s 2/2=5.5

7. Here’s a good one to think about.  A public health researcher tested the hypothesis that providing new car buyers with child safety seats will also act as an incentive for parents to take other measures  to protect their children (such as driving more safely, child proofing the home, etc.) Dr. L counted all the occurrences of safe behaviors in the cars and homes of the parents who accepted the seats versus those who did not.  The findings? A significant difference at the .013 level.  Another researcher did exactly the same study, and for our purposes, let’s assume that everything was the same—same type of sample, same outcome, measures, same car seats, and so on. Dr. R’s results were marginally significant at the .051 level.  Whose results do you trust and why?

8. Here are the results of the three experiments where the means of the two groups being compared are exactly the same but the standard deviation is quite different from experiment to experiment. Compute the effect size using the formula (ES=x1-x2/SD)and then discuss why this size changes as a function of the change on variability.