I'm a little confused about hypothesis tests and the wording in the problems. Can I use the hypothesis test method to answer a problem even if the problem doesn't ask "does it support the claim"?
For example, the question asks
"In a random sample of HIV test results, 37 test results were positive and 1,383 were negative. Using a confidence level of 99%, is the population for positive test results greater than 2%?"
It doesn't ask to support a claim but can I use the method anyways?
n = 1,420
p hat = .0261
alpha = .01
z = invnorm (.99) = 2.33
z = [.0261 - .02] / [sq rt (.02*.98)/1420] = 1.64
So then I'd say, there's insufficient evidence to support the claim that the population is greater than 2%.
Am I doing this correctly??
For example, the question asks
"In a random sample of HIV test results, 37 test results were positive and 1,383 were negative. Using a confidence level of 99%, is the population for positive test results greater than 2%?"
It doesn't ask to support a claim but can I use the method anyways?
n = 1,420
p hat = .0261
alpha = .01
z = invnorm (.99) = 2.33
z = [.0261 - .02] / [sq rt (.02*.98)/1420] = 1.64
So then I'd say, there's insufficient evidence to support the claim that the population is greater than 2%.
Am I doing this correctly??
-
M -
You made one mistake ... this is a "one-tail" test because they are only asking if the test results are GREATER THAN 2%. So, z-alpha = 2.054.
Fortunately, you will get the same decision to NOT REJECT the null hypothesis that the proportion is 2%.
Otherwise, you did a GREAT JOB ... keep up the good work!
Hope that helps
You made one mistake ... this is a "one-tail" test because they are only asking if the test results are GREATER THAN 2%. So, z-alpha = 2.054.
Fortunately, you will get the same decision to NOT REJECT the null hypothesis that the proportion is 2%.
Otherwise, you did a GREAT JOB ... keep up the good work!
Hope that helps