In: Statistics and Probability
step 1: You want to compare the daily number of hits for two different MySpace page designs that advertise your indie rock band. You assign the next 30 days to either Design A or Design B, 15 days to each. Would you use a one-sided or two-sided significance test for this problem? True or False: We use a two-sided significance test because we do not suspect that one design will be better than the other.
step 2: You want to compare the daily number of hits for two different MySpace page designs that advertise your indie rock band. You assign the next 30 days to either Design A or Design B, 15 days to each. If you use Table D to find the critical value, what are the degrees of freedom using the second approximation? Give your answer to the nearest integer. Fill in the blank: The degrees of freedom are: df =
step 3: You want to compare the daily number of hits for two different MySpace page designs that advertise your indie rock band. You assign the next 30 days to either Design A or Design B, 15 days to each. If you perform the significance test using , how large (positive or negative) must the statistic be to reject the null hypothesis that the two designs result in the same average hits? The absolute value of the -statistic must be at least,
Step 1
Two sided significance test would be used to compare the daily number of hits for two different my space page designs.
This is because no claim is made against which design is thought to be better than the other, so we just need to test whether or not the daily number of hits are same for both the designs.
True
This is true because as i mentioned before we do not suspect that one design will be better than other.
Step 2
As table D is not given in the question as my number of observations change my degrees of freedom will also change, so depending upon the number of observations df will be decided.
Step 3
Depending upon the df and the level of significance we can get a table value above which the null hypothesis would be rejected that is if absolute value of calculated statistic is greater than the table value than null hypothesis is rejected.