George claims that 45% of voters would vote for him to win.
In an opinion poll of 20 voters only 5 would vote for him.
Test at 5% significance level whether or not there is sufficient evidence to support Georges claim.
So, from this information I have deduced that:
Ho: p=0.45
H1: p is not equal to 0.45
therefore it is a 2 tailed test, but in the markscheme they use a One tailed test.
How do i know when to use a one tailed vs two tailed? two tailed is when there has been a change, either an increase or decrease, so the number of voters could be higher or lower than 45%.
In an opinion poll of 20 voters only 5 would vote for him.
Test at 5% significance level whether or not there is sufficient evidence to support Georges claim.
So, from this information I have deduced that:
Ho: p=0.45
H1: p is not equal to 0.45
therefore it is a 2 tailed test, but in the markscheme they use a One tailed test.
How do i know when to use a one tailed vs two tailed? two tailed is when there has been a change, either an increase or decrease, so the number of voters could be higher or lower than 45%.
-
Strictly speaking you are correct. However, George is unlikely to claim that
fewer that 45% will vote for him so I would have H1:p>0.45
Normally you will be told when to use a one-tailed test and you should
use a two-tailed test unless there is a strong reason not to.
I think you would get a high proportion of the marks for the question if you
used a 2-tail accurately.
fewer that 45% will vote for him so I would have H1:p>0.45
Normally you will be told when to use a one-tailed test and you should
use a two-tailed test unless there is a strong reason not to.
I think you would get a high proportion of the marks for the question if you
used a 2-tail accurately.