Regressions

Question 1

Pearson’s Correlation

Answer 1

1. Something that can be used t measure an effect size
2. Varies between -1-1
3. A correlation coefficient of zero indicates there is no relationship between the variables

Question 2

Correlation = .12, p=<.01
What is the relationship between the two variables

Answer 2

Small, but significant

Question 3

Pearson’s Correlation of -.1 is

Answer 3

Mildly good fit

Question 4

Pearson’s Correlation of .5

Answer 4

Moderately good fit

Question 5

Pearson’s Correlation of .8

Answer 5

Strong good fit

Question 6

If r=.67 then the variables…

Answer 6

share variance

Question 7

Coefficient of Determination

Answer 7

Measure of the amount of variability in one variable that is shared by the other

Question 8

Pearson’s Correlation of -.71, n=300

Answer 8

Strong negative relationship

Question 9

if r=.21 then the effect is

Answer 9

small to medium

Question 10

Multicollinearity

Answer 10

When predictor variables correlate very highly with each other

Question 11

T-Statistics are not:

Answer 11

equal to the regression coefficient divided by its standard deviation

Question 12

Multiple Regression Assumptions

Answer 12

• Continuous outcome variable, and continuous or dichotomous predictor variables
• Independence
• Non-zero variance:
• No Outliers
• No Perfect or High Multicollinearity
• Homoscedasticity
• Linearity
• Normally Distributed Errors
• Independent Errors (Residuals)

Question 13

Independence (MR Assumption)

Answer 13

All values of the outcome variable should come from a different participant

Question 14

Non-Zero Variance (MR Assumption)

Answer 14

The predictors should have some variation in value, e.g. variances ≠ 0

Question 15

No Outliers (MR Assumption)

Answer 15

• No data points outside 3 SD’s from the mean
• Generally 1% outliers ok

Question 16

No Perfect or High Multicollinearity (MR Assumption)

Answer 16

Predictor variables should not have multicollinearity

Question 17

Homoscedasticity (MR Assumption)

Answer 17

Variance of residuals should be similar across of the scores on the continuum

Question 18

Heteroscedasticity (MR Assumption)

Answer 18

Variance of residuals (errors) differs across the variable continuum

Question 19

Linearity (MR Assumption)

Answer 19

There exists a linear relationship between the predictor variables and the outcome variable and the predictor variables combine additively

Question 20

Normally Distributed Errors (MR Assumption)

Answer 20

Residuals follow bell curve

Question 21

Independent Errors (MR Assumption)

Answer 21

The errors between pairs of observations should not be correlated, e.g. if observations are made over time it is likely that successive observations would be correlated
Tested with Durbin-Watson Test
Needs to be between 1.5-2.5

Question 22

Pearson’s R

Answer 22

Standardized version of covariance
Cannot be used to determine causation

Question 23

Regression

Answer 23

Predicting variable y (outcome) from variable x (variable)