Q9 Correlation

Question 1

Correlation

Answer 1

A relationship between two measures that change together

Question 2

“Relationship”

Answer 2

• May or not be causal
• Correlation does not imply causation

Question 2

“Measures”

Answer 2

In data, measures are known as variables

Question 2

Ways data can “change together”

Answer 2

• Increase together
• Decrease together
• Go in opposite directions

Question 3

Correlations are crucial to . . .

Answer 3

Science

Question 4

Plausible alternative explanation

Answer 4

A rival rationale that might better explain an observed relationship, or a third variable that could be impacting the correlation

Question 5

Variable

Answer 5

A unit of measurement that has the potential to vary or change

Question 6

Four types of variables

Answer 6

• Nominal
• Ordinal
• Interval
• Ratio

Question 7

Nominal

Answer 7

• Means name, like “nombre” in Spanish
• Gives a name to things without any order or rank

Question 8

Ordinal

Answer 8

• A nominal variable whose measurements have an order or rank
• The gaps between each rank may not be equal

Question 8

Interval

Answer 8

• Ordinal variables where the gaps between each rank are equal
• “Interval” refers to the size of the units
• No true zero

Question 9

Ratio

Answer 9

• Measures equal units, such as elapsed time
• Has a true zero
• Zero could also mean the absence of a measurement, like weight

Question 10

Type of variable: Religions

Answer 10

Nominal

Question 11

Type of variable: Letter grades

Answer 11

Ordinal

Question 12

Type of variable: A temperature scale of Fahrenheit

Answer 12

Interval

Question 13

Type of variable: A clock

Answer 13

Interval

Question 14

Type of variable: Stopwatch

Answer 14

Ratio

Question 15

Categorical variables

Answer 15

• Nominal & Ordinal
• Coarse measure
• Less sensitive to statistics, but can still detect correlation

Question 15

Type of variable: Money

Answer 15

Ratio

Question 16

Continuous variables

Answer 16

• Interval & Ratio
• Refined measure (specific)
• More sensitive to statistics, making it easier to detect correlation

Question 17

X-axis

Answer 17

Independent variable

Question 18

Y-axis

Answer 18

Dependent variable

Question 19

Positive correlation

Answer 19

Two measures increase together or decrease together

Question 20

Negative correlation

Answer 20

As one measure increases, the other decreases

Question 21

What do positive and negative correlations have in common?

Answer 21

They are causations

Question 22

A correlation can be a causation if:

Answer 22

• The change is unidirectional
• The change is direct, without a plausible alternative explanation

Question 23

Unidirectional example with height and weight

Answer 23

• Height causes weight
• Weight does not cause height

Question 24

Direct change without a plausible alternative explanation example with height and weight

Answer 24

While factors like diet also cause weight, the influence of height is direct

Question 25

Causal relationships and correlations

Answer 25

Every causal relationship is a correlation, but not every correlation is a causation

Question 26

Association

Answer 26

• A mutual relationship between two variables that can either be causal, or only a correlation
• Either variable can be the independent variable

Question 27

Correlation between pay and gender

Answer 27

• Complicated because people and the soceieties we exist in are complicated
• So many variables involves, so causality is hard to pinpoint

Question 28

Correlation between ice cream and swimsuits sales

Answer 28

• Plausible alternative explanation: summer

Question 29

Correlation between having a strong interest in the arts and living in the city

Answer 29

• Association
• You could be interest in arts because you live in the city
• Or you could move to the city because you’re interested in arts

Question 30

Correlation between people who watch crime shows and having mean world syndrome

Answer 30

• Association
• People could have mean world syndrome because they watch crime shows
• Or people could watch crime shows because they have mean world syndrome

Question 32

How can researchers determine if correlations are meaningful?

Answer 32

Statistics

Question 32

Statistical significance tests

Answer 32

Determine if a relationship among variables exists beyond chance, with some allowable error

Question 32

Spurious relationship

Answer 32

A correlation of unrelated variables, or a coincidence

Question 32

What does “beyond chance” mean?

Answer 32

• p < .05 refers to the amount of error allowed
• p is probability
• .05 is 5%
• Less than 5% chance correlation in error

Question 33

Relationship between a Gator victory and your lucky socks

Answer 33

Spurious relationship

Question 34

Testing a correlation while testing a second one

Answer 34

Test the control, which could be a placebo, another treatment, or no treatment at all

Question 35

Experiment

Answer 35

Comparing correlation for two or more conditions

Question 36

Good experiment

Answer 36

• Participants must be assigned the conditions at random (random assignment)
• Participants cannot know what condition they’re in, and neither can the practitioners (double-blidn study)
• These factors reduce bias

Question 37

Randomized controlled trial

Answer 37

Tests a treatment against a control with participants assigned at random, and if possible, is double-blind

Question 38

If the treatment is stronger than the control . . .

Answer 38

The treatment is causal

Question 39

Split testing in media

Answer 39

Compares two messages, A and B

Question 40

Sending ad tweets two weeks apart using different wording for each

Answer 40

• Split testing
• Online analytics determine what generates more engagement