Power Analysis Flashcards

1
Q

A statistical tests power is the probability that it will…

A

Avoid Type 2 error/correctly pick up on an effect

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

This hypothesis states that the difference between the two variables is zero

A

Null

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

One motivation for conducting a study is to provide evidence that the hypothesis is true. We do this by showing…

A

The null hypothesis is unlikely

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

A Type 1 error is where

A

False positive

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

A Type 2 error is a

A

False negative

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

“Rejection of the null, when it is in fact true”

A

Type 1 error

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

What is an effect?

A

What was found

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

What is effect size

A

Measures strength of result - magnitude-based

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

Difference between EFFECT SIZE and SIGNIFICANCE?

A

Effect size does not depend on sample size

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

The p value indicates if what was found is g..

A

Generalisable to a population

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

Effect size does not depend on

A

Sample size

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

If we find a non-significant p-value despite a large effect, this is likely because

A

Small sample

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

A prospective power analysis shows us that a certain ________ are needed to yield a significant result

A

Number of pps

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

Sufficient power to find statistical significance minimises

A

Chance findings

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

A power analysis is where one of several _______________ can be calculated given others

A

Statistical parameters

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

There are ___ parameters involved in a power analysis

A

4

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

4 parameters involved in a power analysis

A

(i) Alpha
(ii) Power
(iii) N
(iv) Effect size

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

Coefficient alpha is the p…

A

Probability of finding significance where there is none - Making a Type 1 Error

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

Coefficient alpha is usually set to

A

.05

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Power is usually set to

A

.80

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Power is the probability of finding

A

True significance

22
Q

Power is the probability of avoiding

A

A type 2 error

23
Q

Power analysis

The parameter usually solved for is…

24
Q

Expected effect size may be ascertained from… (4)

A
  1. Pilot study
  2. Findings from similar study
  3. Field defined ‘meaningful effect’
  4. Educated guess
25
Alpha is usually set to ___ and power is usually set to ___
.05 | .80
26
When trying to ascertain effect size, if there are no similar studies...
Start with pilot study
27
There are FOUR TYPES OF POWER ANALYSIS
Priori Post-hoc Criterion Sensitivity
28
For a priori, you'd compute ___. The rest is given
Sample size (N)
29
For a post-hoc, you'd compute ____. The rest is given
Power
30
For a criterion, you'd compute ___. The rest is given
Alpha
31
Which type of power analysis is USUALLY DONE
Priori
32
A 72% power indicates that you have a 72% chance of
Avoiding making a Type 2 error/Picking up on an effect
33
Power is increased when a researcher increases
Sample size/Effect Levels/Significance Levels
34
_______ is increased when a researcher increases sample size/effect levels/significance levels
Power
35
How to calculate effect size
M1 + M2 / SD (collective)
36
A power analysis is where
One of several statistical parameters can be calculated given others
37
Reporting a prospective priori order
1. Pps 2. Effect size 3. Alpha 3. Power
38
Reporting a sensitivity order
1. Pps 2. Effect size 3. Alpha 4. Power
39
Reporting a post-hoc
1. Effect size 2. Pps 3. Alpha 4. Only achieved 73% power
40
How do you begin reporting a post-hoc
The effect size for this study was calculated as
41
How do you begin reporting a retrospective priori
The effect size for this study was calculated as
42
Statistical power depends on (3)
1. Effect size 2. Sample size 3. Precision of measures
43
Why does statistical power depend on precision of measures?
More reliable measures = smaller SE's/more precise variable estimates
44
Effect size The ______ the better
Larger
45
Sample size Larger sample size =
Smaller SE's
46
Error bars Small samples will have
Large error bars
47
Error bars Easier to estimate when
Error bars are smaller
48
Large error bars = _____ sample size
Small
49
Prospective power analysis We don't want to recruit too many pps
As this could result in significant result regardless of effect size
50
Other than a Priori, you could calculate required sample size
Using Cohen's table
51
Why does sample size affect power
Larger = smaller SE's | Small, non-overlapping error bars