Correlation Flashcards

1
Q

What are 3 obstacles to experimentation?

A

Ethical (harmful), credibility and practical (can’t manipulate) problems

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

What is the full name for r?

A

Pearson product-moment correlation coefficient

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

What is r? (What is another name)

A

An index of strength of relationship between two variables (aka zero-order correlation)

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

What typifies a correlation of 0?

A

No relationship - No tendency for a higher score on one to be associated with a higher or lower score on the other; the mean is the best predictor.

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

What is the numerator in covariance ?

A

The summed products of deviation scores.

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

Why is covariance dependent on the scale of the measured variables?

A

Because it is not standardised (taking into account z scores)

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

What does a test for the significance of r reveal?

A

Whether the linear relationship exists in the population, or if its likely due to sampling error.

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

What is rho?

A

The correlation coefficient in the population

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

What is the population correlation coefficient (rho) under the null hypothesis?

A

0, and it is normally distributed.

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

What are the degrees of freedom when testing significance of r?

A

N-2

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

What happens to the significance of r as N increases?

A

Smaller r values can reach significance

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

What size of r value would be significant for N= 52 and N=102?

A

.27 & .19

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

What is k^2? What does it refer to?

A

The coefficient of non-determination, or 1-r^2. 
Amount of variance that cannot be predicted by the other variable (residual/error).

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

When would you use point-biserial correlation?

A

When one variable is genuinely dichotomous, having 2 levels. (Yes/no, present/absent, left/right, etc)

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

What can affect the sign of a correlation using point-biserial?

A

How the dichotomous variable is labelled. Swapping 0 and 1 results in inverting the sign.

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

The result of significance test for r_pb and t-test are _____?

A

Identical.