Stats Final

Question 1

Correlation

Answer 1

Correlations test the extent to which variables are
related to one another.

Question 2

Simple (“Bivariate”) Correlation

Answer 2

assesses the
relationship between two variables.
To use bivariate correlation:
● The same sample must be measured on two
variables
● Both variables must be measured with
continuous data

Question 3

Pearson r Product-Moment Correlation Coefficient

Answer 3

Direction (type of relationship)
○ Positive (direct): as X increases, Y increases
○ Negative (inverse): as X increases, Y decreases

Magnitude
○ Range of values for r: -1 ← 0 → +1
○ The farther away from 0 (in a pos or neg direction), the stronger the
relationship “Closeness to the line”

Question 4

Correlation Coefficient Magnitudes (3)

Answer 4

r=+1, r=-1,r=0

Question 5

r = +1

Answer 5

A perfect linear positive relationship. All observations follow a
linear regression line with positive slope (SSE = 0)

Question 6

r = -1

Answer 6

A perfect linear negative relationship. All observations follow a
linear regression line with negative slope (SSE = 0)

Question 7

r = 0

Answer 7

There is no linear relationship between two variables (although
there can be non-linear relationship)

Question 8

± 0.3

Answer 8

Usually don’t exceed

Question 9

Testing for Statistical Significance

Answer 9

Testing for statistical significance involves testing the Pearson r to see
likelihood that observed relationship is not due to chance sampling error. (Ask: ● Hours of crime dramas watched (“How many hours of crime shows did you watch
this week?”)

● Fear of crime (“How likely are you to be a victim of crime?”)
Conduct a test with 𝛂 = .01.)

Question 10

Correlation

Answer 10

a necessary condition for a causal relationship, but not a
sufficient condition

Question 11

Regression, covariance, and correlation

Answer 11

based on the same conceptual
background - All three provide information about whether or not two variables stand in
a linear relationship

Question 12

Correlation analysis

Answer 12

provides one simple coefficient that information us
about the strength of the relationship, whereas regression enables us to
predict values of the DV when knowing values of the IV.

Question 13

What are the criteria that allow you to determine causality?

Answer 13

Spuriousness, correlation, correlation techniques to falsify, sophisticated statistical tests

Question 14

casual relationship

Question 15

Significant r

Answer 15

tells us that the relationship is not likely due to sampling
error, but it does not tell us meaning of the relationship

NOT SAMPLE ERROR, NOT MEANING

Question 16

Plain Language

Answer 16

The more the more, the more the less, there is no r(df) = r, p <.05

Question 17

Magnitude

Answer 17

○ Range of values for r: -1 ← 0 → +1
○ The farther away from 0 (in a pos or neg direction), the stronger the
relationship “Closeness to the line”

Question 18

Coefficient of Determination

Answer 18

Tells us about shared variance.
Technically: the proportion of
variance in one variable that can
be accounted for (or explained
by) variance in another variable.

Number between 0-1 which tells us the variance

Question 19

Why correlation is not causation

Answer 19

Spurious
Sample size
Sampling Error
X -> Y? Y-> X? Z?

Question 20

Bivariate Linear Regression

Answer 20

allows you to
predict values of one variable from values
of another variable.
(Ad spend -> Increased revenue)

Question 21

Regression Line

Answer 21

A regression line or “line of best fit” is drawn to
minimize the vertical distance between the line and
all data points.
We usually find it with y=mx+b