Lecture 11 Conceptual Short-Answer Flashcards
Exam 3
What is Null hypothesis significance testing (NHST)?
Refers to a statistical procedure that determines whether there is enough evidence to support a research hypothesis about population parameters
H0 and Ha must be mutually exclusive and exhaustive. What does it imply?
There are only 2 possible states H0 is true or Ha is true (one is true if and only if the other is false)
What is the critical value in the null hypothesis significance testing?
The value such that the probability of the test statistic exceeding this value is a, assuming the null hypothesis is true
(a cut-off point used to determine whether to reject the null hypothesis in a hypothesis test)
What is the p value in the null hypothesis significance testing?
The chance of observing a result as extreme as, or more extreme than your result, assuming that H0 is true
What is the Type I error?
Rejecting the null hypothesis when it is true
What is the Type II error?
Failing to reject the null hypothesis when it is false
What is the statistical power?
The probability that a test will correctly reject H0 when H0 is false
Justify in one sentence why stating μ ≤ 2,000 for the null hypothesis, even though μ = 2,000 is the
default. Also, explain in one sentence the limitation of the statement “H0: μ = 2,000 and Ha: μ > 2,000”.
1) For the directional hypothesis, we use this condition just because if the null of μ = 2000 can be
rejected, then every other possible μ value less than 2000 (e.g., μ = 1,999, μ = 1,998,…, μ = 0) can
also be rejected.
2) “H0: μ = 2,000 and Ha: μ > 2,000” is not exhaustive
- or two hypotheses do not cover all the possible values of μ
- or rejecting H0 does not results in supporting Ha in this condition.
When can you choose a one-tailed, one sample z-test?
1) we need to compare 𝑋̅ to 𝜇
2) 𝜎 is known
3) 𝐻𝑎 is directional
When can we choose a two-tailed, one-sample Z-test?
1) we need to compare 𝑋̅ to 𝜇
2) 𝜎 is known
3) 𝐻𝑎 is non-directional
