Lecture 6A: Hypothesis Testing Flashcards

1
Q

What is a statistical hypothesis?

A

A statement about the numerical value of an unknown parameter.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is the null hypothesis (H0)?

A

Assume no difference/association.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What does H0: μ1- μ2=0 imply?

A

There is no significant difference

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What does H0: ρ=0 signify?

A

There is no significant association.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is the purpose of inferential statistics?

A

To determine whether the differences/associations found in a study are true or due to chance.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What are the five steps in hypothesis testing?

A
  1. State the statistical (null) hypothesis to be tested.
  2. Determine alpha value
  3. Run descriptive stat
  4. Run inferential stat and find p-value
  5. Make decision regarding null hypothesis

Null hypothesis assumes no diff/association

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is the alpha value in hypothesis testing?

A

The maximal acceptable risk of making a type I error, usually set at 0.05

Type I error: Incorrectly concluding null hypothesis is false

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is a type I error?

A

Incorrectly concluding that the null hypothesis is false when it is true.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What does p-value represent in hypothesis testing?

A

The probability of finding a result as extreme as the observed result, assuming H0 is true.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What decision is made if p < α?

A

Reject the null hypothesis.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is the conclusion if p > α?

A

Accept the null hypothesis (No significant diff)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is a type II error?

A

Accepting the null hypothesis when it is false, denoted by β

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is the relationship between sample size and power?

A

Larger sample size increases power (1-β).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What happens when the sample size is small?

A

Increased β leads to decreased power.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is the conclusion if p = 0.036 in a study with α set at 0.05?

A

Reject the null hypothesis.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is the risk of making a Type I error when p = 0.036?

A

3.6% chance of incorrectly rejecting H0.

17
Q

What is the correct interpretation of a p-value of 0.02?

A

There is a 2% chance of making a Type I error if the null hypothesis is rejected.

18
Q

What does the power of a study indicate?

A

The ability to find a difference when one truly exists.

19
Q

What is the effect of increasing sample size from 63 to 126?

A

Increased likelihood of detecting a significant difference.