L8- Correlations Flashcards

You may prefer our related Brainscape-certified flashcards:
1
Q

What are correlations?

A

Correlations- technique for analysing strength of relationship between 2 quantitative variables (co-variables)

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

Where is data for a correlation obtained from?

A

Data for correlation usually obtained from non-experimental source e.g. survey

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

What are the types of correlation that can be seen?

A

1) ➕ correlation – as 1 variable ⬆️ the other variable ⬆️ as well
2) ➖ correlation – as 1 variable ⬆️ the other variable ⬇️
3) ✖️ correlation – ✖️ relationship between the 2 variables at all

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

What can the strength of a correlation range between and what does it signify?

A
  • Strength of a correlation can be between -1 and 1
  • 0 =✖️ correlation
  • -1 = 💪 ➖ correlation
  • +1 = 💪 ➕ correlation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is the strength of a correlation known as?

A

Correlation coefficient

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

What do the 4 (yes 4) types of correlation look like?

A

See L8 handout- A2 research methods- word doc

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

What are the advantages of correlations?

A

👍- allows psychologists to establish strength of relationship between 2 variables and measure it precisely
👍- allows researchers to investigate things that could not be manipulated experimentally for ethical or practical reasons- e.g. effect of stress on cholesterol levels- use of data from non- experimental source
👍- once correlation conducted- predictions about 1 of the variables can be made based on what is known about other variable

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

What are the disadvantages of correlations?

A

👎- ✖️ demonstrate cause and effect- ✖️ tell which variable influences other
👎- despite correlation between 2 variables- variables may not be actually related BUT there is a 3rd unknown variable which influences both (confounding variable)
👎- only measure linear relationships and ✖️ detect curvilinear relationships (➕ relationship up to certain point but after that relationship becomes ➖ or vice versa)

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