2.6/2.7: Correlations Flashcards

1
Q

What are z scores used for?

A

To compare statistics from different studies that may have different units being compared.

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

What are correlational designs referred to as?

A

Observational

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

What do correlational designs measure?

A

Only measurable variables

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

What do correlational deigns occur with?

A

Association claims

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

What is the goal of correlational designs?

A

To detect relationships in variables as they naturally occur.

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

What are the 3 characteristics of Pearson’s correlation statistic?

A
  1. Both variables are at least interval (continuous)
  2. Both variables are normally distributed in the population
  3. The association can be summarized with a straight line (linear)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Correlation Statistic

A

Describes the strength and direction of the relationship between two quantitative variables.

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

What are correlation statistics only used for?

A

Linear relationships that can be modeled with a straight line

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

How is the strength of correlation visually estimated?

A

How close the points are to the trend line.

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

What is the range for strength of correlation?

A

-1 to 1

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

How is the direction of a linear model shown?

A

By the slope (pos/neg)

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

“r”

A

A unitless descriptive statistic

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

What does r not relfect

A

Original units of the variables

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

What is true about effect studies?

A

They are comparable across different variables and studies

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

What is the formula for “r”

A

(Z score of X * Z score of Y) / (N-1)

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

Association Claims

A

Assert that two variables are related to each other

17
Q

What is true about the frequency in association claims?

A

The frequency of one variable is tied to the frequency of another.

18
Q

What does the Pearson correlation statistic support?

A

Association claims

19
Q

What do extreme values in a data set have an impact on?

A

The correlation value of the data set

20
Q

What can outliers do to the correlation value?

A

Increase, mute, or decrease the correlation

21
Q

When there is no correlation between variables, what value is the correlation around?

A

0 - Not exactly 0

22
Q

How are strong correlations presented in the graph?

A

Tightly bound to the line of slope

23
Q

What correlation score do vertical lines have?

24
Q

What do vertical lines have a correlation score of exactly 0?

A

A relationship cannot be determined due to the same x value having multiple y values

25
Q

What 2 ways help you protect your data set from outliers?

A
  1. Check one variable distribution for the present outliers first (identify)
  2. Look at the scatter plots before interpreting the correlation value (identify outlier influence)
26
Q

What do Z Scores tell us?

A

How many units a value variates from the mean, in terms of standard deviation.

27
Q

What happens to the z score of a value when the value is below the mean?

A

It will be negative

28
Q

How do you calculate the z score of a value?

A
  1. Find variation from the mean
  2. Divide the variation by the standard deviation
29
Q

How do outliers in the same direction of the slope affect the correlation?

A

Increases the strength of the relationship (more + or -)

30
Q

How do outliers in the opposite direction of the slope affect the correlation?

A

Decreases the strength of the relationship (closer to 0)

31
Q

What effect does taking out extreme values have on the correlation value of the data set?

A

Increases the correlation (stronger)

32
Q

What should you do if the outlier is proved to be a mistake in the data?

A
  1. Remove the value
  2. Report the removal in the methods section; explain what impact it had on the data / why it was an outlier.