Regression

Question 1

Multivariate Designs

Answer 1

A study designed to test an association Involving more than two measured variables.

Question 2

What are the 3 criteria to establish causation?

Answer 2

Covariance

Temporal Precedence

Internal Validity; third variables

Question 3

Linear Regression

Answer 3

The model that estimates the relationship/ preidcted relationship between two variables.

Question 4

When is linear regression appropriate?

Answer 4

when you want to predict a continuous outcome based on one or more predictor variables.

Question 5

When can you use linear regression?

Answer 5

• When the relationship between X and Y is linear
• When variables are quantitative

Question 6

What are the two parts of linear regression?

Answer 6

a= Intercept

b1= slope

Question 7

What does the intercept of linear regression mean?

Answer 7

The predicted score for someone who ___ for 0 ____.

Question 8

What does the slope of linear regression mean?

Answer 8

The amount Y changes when X increases by 1 unit.

Question 9

What 3 things are used to assess the model of fit for linear regression?

Answer 9

1. Sum of Squares
2. Root Mean Squared Error (RMSE)
3. R-Squared (R^2)

Question 10

Sum of Squares of Y given X

Answer 10

Measures the total squared differences between observed Y and predicted Y.

Question 11

What value of sum of squares indicates a better model fit?

Answer 11

A smaller sum

Question 12

RMSE (Root Mean Squared Error)

Answer 12

The typical size of prediction errors.

Question 13

What value of RMSE indicates a better model fit for linear regression?

Answer 13

A smaller value

Question 14

What units are RMSE in?

Answer 14

The same units as Y

Question 15

R-Squared (R^2)

Answer 15

Proportion of variance in Y explained by X.

Question 16

If R^2 = 0.25, what does that mean?

Answer 16

25% of variance in ___ is explained by ___ variability.

Question 17

Longitudinal Design

Answer 17

A study in which the same variables are measured in the same people at different points in time.

Question 18

What can longitudinal designs provide evidence for?

Answer 18

Temporal Precedence

Question 19

What can longitudinal designs be adapted to do?

Answer 19

Test causal claims

Question 20

Cross Sectional Correlations

Answer 20

A correlation between two variables that are measured at the same time.

Question 21

What can cross sectional correlations not measure?

Answer 21

Temporal precedence

Question 22

Autocorrelations

Answer 22

The correlation of one variable with itself, measured at two different times.

Question 23

Cross-Lag Correlations

Answer 23

A correlation between an earlier measure of one variable and a later measure of another variable.

Question 24

What are cross lag correlations considered?

Answer 24

The primary interest of researchers

• address directionality and establish temporal precedence

Question 25

What can cross lag correlations investigate?

Answer 25

how one variable correlates with another one over time.

Question 26

When is b significant?

Answer 26

When the p value is less than 0.05

Question 27

When is β used?

Answer 27

- Interpreting raw results - Comparing values across variables

Question 28

What does the p-value show?

Answer 28

If the effect is statistically significant.

Question 29

What does R^2 show?

Answer 29

How much the variance in data is explained

Question 30

What does RMSE show?

Answer 30

The typical error size

Question 31

Multiple/Multivariate Regression

Answer 31

A statistical technique that computes the relationship between a predictor variable and a criterion variable, controlling other predictor variables.

Question 32

What does multivariate regression help rule out?

Answer 32

Third variables; address internal variability concern

Question 33

Controlling For

Answer 33

Holding a potential third variable at a constant level while investigating the association between two other variables.

Question 34

Criterion Variable

Answer 34

The variable in a multivariable regression analysis that researchers are most interested in understanding or predicting. - Known as dependent variable

Question 35

Predictor Variables

Answer 35

A variable in multivariable regression that is used to explain the variance in the criterion variable. - Known as independent variable.

Question 36

What does a positive b value indicate?

Answer 36

a positive relationship between the predictor variable and criterion variable.

Question 37

What does a negative b value indicate?

Answer 37

a negative relationship between the predictor variable and criterion variable.

Question 38

What does the higher the b value mean?

Answer 38

the stronger the relationship between the predictor variable and criterion variable.

Question 39

What can adding several predictors to a regression analysis do?

Answer 39

- Control for several third variables at once. - Get a sense of which other factors predict the dependent variable.

Question 40

Mediator

Answer 40

A variable that helps explain the relationship between two other variables.

Question 41

What validity is the mediator focused on?

Answer 41

Internal Validity

Question 42

Third Variable

Answer 42

Determined if a confounded is present in the data results.

Question 43

What validity is the third variable focused on?

Answer 43

Internal validity

Question 44

Moderator

Answer 44

A variable that changes the relationship between two variables.

Question 45

What validity is the moderator focused on?

Answer 45

External validity