chapter 9: hypothesis testing Flashcards
null hypothesis (H0)
the statement being tested
the null hypothesis is given the benefit of the doubt
not rejected unless there is a convincing sample that rejects it
alternative hypothesis (Ha)
statement that is assigned the burden of proof
is accepted only if there is conning sample evidence that it is true
in the null hypothesis testing, what is easier to establish first?
the. null hypothesis
you define the alternative hypothesis later on
what is the two sided, not equal to alternative thingy?
when the alternative hypothesis (Ha) is simply not equal than the null hypothesis
what is the one sided, greater than alternative thingy?
when the alternative hypothesis (Ha) is greater than null hypothesis
or vice versa
what is the one sided, less than alternative thingy?
when the alternative hypothesis (Ha) is less than null hypothesis
or vice versa
how doe we always formulate the null and alternative hypothesis?
in a way that involves an equality
when do we reject a certain hypothesis in favor for its alternative using the test statistic?
when the z value is far enough from zero
what is a type 1 error?
when we reject the null hypothesis (H0) when its true
what is a type 2 error?
when we don’t reject the null hypothesis (H0) when we should
what is the symbol denoted alpha?
the probability of Type 1 error
what is the symbol denoted Beta?
the probability of Type 2 error
if alpha is small ale¡ready, but gets even smaller by choice, what happens to Beta?
it becomes bigger
whats the minimum alpha we usually set?
0.01
setting one smaller than that will result in a Beta too big
what is the critical value rule
where we know the accepted value of alpha, we then use the sampling distribution of the test statistic z
we only reject the null hypothesis in favor of the alternative hypothesis (or vice-versa) if the z value is bigger than Z alpha (will give a value of right hand tail)
what is the level of significance of a test
the probability of a Type 1 error
when do we have a statistical significance at a certain alpha level?
if we can reject the null hypothesis in favor of an alternative hypothesis at that level of significance alpha
what is the p value
an alternative to using a critical value
the probability that we see a Z value that contradicts our null hypothesis even though this null hypothesis is true
it is the found Z value that will contradict the null hypothesis if its
when do we choose to reject the null hypothesis with p value and z value
the Z value found must be greater than the corresponding z value of alpha
when the probability corresponding to the Z p value (right hand tail thing) is smaller than alpha
what does it mean if the p-value for testing the null hypothesis (H0) is 0.10?
we have some evidence that the null hypothesis is false
what does it mean if the p-value for testing the null hypothesis (H0) is 0.05?
we have strong evidence that the null hypothesis is false
what does it mean if the p-value for testing the null hypothesis (H0) is 0.01?
we have very strong evidence that the null hypothesis is false
what does it mean if the p-value for testing the null hypothesis (H0) is 0.001?
we have extremely strong evidence that the null hypothesis is false
