Topic 5 Flashcards

1
Q

What variables are talked about in correlation?

A

Dependent only

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

If variables are related they are said to be…

A

Correlated

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

Does correlation include Independent variables? What is the consequence of this?

A

No, therefore it can only be used to describe and predict but NOT explain/infer causality

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

Explain positive correlation and how the graph represents this

A

As one variable increases, the other increases

The graph plots tilt upwards from Left to Right

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

Explain negative correlation and how the graph represents this

A

As one variable increases, the other decreases

The graph plots tilt downwards from Left to Right

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

Explain zero correlation and how the graph represents this

A

There is no consistent relation between variables

The plots are scattered with no pattern

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

Describe a strong correlation

A

Scores are more closely groups around an imaginary line

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

What does a stronger correlation give?

A

Better predictability

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

What is the numerical way to express correlation?

A

Pearson R

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

What values does r range between?

A

-1 to +1

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

To correlate variables how must they be measured

A

Measured on the same individual

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

What 2 scales must the correlation variable be measured on?

A

Interval or ratio scale

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

TRUE or FALSE

r can detect all relationships

A

FALSE

r can only detect linear relationships

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

What does it mean when r = 0, or is low?

A
  • May mean no relationship
  • The relationship might be non-linear
  • Range could be restricted i.e not enough spread/variability
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Describe a curvilinear relationship

A

Increase in x initially increases y, then decreases y

e.g. Yerkes-Dodson arousal curve

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

What does the Cross-Lagged-Panel correlation procedure help deal with?

A

With directionality, see which variable causes what

i.e x -> y or y -> x

17
Q

In the Cross-Lagged-Panel correlation procedure what are we most interested in looking at?

A

The diagonals to help get a sense of direction

18
Q

What is the underlying assumption in the Cross-Lagged-Panel correlation procedure?

A

If one variables ‘causes’ other, then it should be more strongly related overtime