Correlation Flashcards

1
Q

What could be an indicator of high variance?

A

Datapoints being further away from their mean (on average).

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

How could we hypothetically calculate variance (the overall measure of how far each datapoint is from their mean)?

A

We could hypothetically just add up each deviation score.

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

What is an example of the reasons that we don’t just add up each deviation score to calculate variance?

A

The positive numbers would cancel out the negative ones.

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

Why do we square each deviation score before adding them up to calculate variance?

A

So that the positive numbers do not cancel out the negative ones.

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

How is variance calculated?

A

The difference between each datapoint and the mean is calculated, squared, added together, and divided by the number of datapoints included in the dataset.

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

To what does covariance refer?

A

To whether when a participant deviates from the mean on one variable, they also deviate from the mean on another variable in a similar or opposite way.

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

What are the different possible types of relationships between variables?

A

A positive relationship (as one variable goes up, the other goes up), negative relationship (as one variable goes up, the other goes down), or no relationship (as one variable goes up, the other does nothing systematic).

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

Of what is covariance a measure, as opposed to revealing anything about more complicated patterns?

A

It is a measure of a linear (straight line) relationship.

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

How can covariance be calculated (similarly to variance)?

A

By taking a given subject’s distance from the mean in x, and multiplying this by their distance from the mean in y, repeating this for all involved subjects, adding all of these values together, and dividing this value by n-1.

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

What is the covariance equation?

A

Cov(x, y) = (Σ(x-x̄)(y-ȳ))/ N-1

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

How does the covariance value established by the covariance equation explain the relationship between an independent and dependent variable?

A

Multiplying two positive values or two negative values will give rise to a positive value, and multiplying one positive value and one negative value will give rise to a negative value, meaning that once we have added together the distances of each variable’s datapoints from each mean, a positive relationship will result in a positive covariance measure, and a negative relationship will result in a negative covariance measure.

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

Of what does the standardisation of the covariance measure provide a measure?

A

Of the strength of the relationship between the two values being investigated (a correlation coefficient).

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

What is the ‘Pearson product moment correlation coefficient’?

A

The covariance measure divided by (sd X x sd Y).

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

To what does the ‘Pearson product moment correlation coefficient’ give rise?

A

To coefficients of between -1 (perfect negative relationship) and +1 (perfect positive relationship).

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

What is ‘Pearson product moment correlation coefficient’ (r)’s formula?

A

r = COVXY/ SXSY

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