Exam 2 Content

Question 1

Relationship of r with cov

Answer 1

Divide by product of standard deviations of X and Y to have r on a standardized scale from 0.00 to 1.00

Question 2

formula for r

Answer 2

Σ(Z_xZ_y)

N-1

Question 3

How to interpret r?

Answer 3

Strength = 0 to 1.00

Direction = +/-

Question 4

4 Characteristics of Scatter Plots

Answer 4

1. Direction (+/-)
2. Strength (0 to 1)
3. Form (linear/curvilinear)
4. Outliers/unusual features

Question 5

Problems with r?

Answer 5

Restriction of range = doesn’t give full picture

Heterogeneous subsamples = doesn’t take into account different “weights” that may affect the slope (and r)

Question 6

When to use r_s?

Answer 6

Use when the data is ordinal

Question 7

Formula for r_s

Answer 7

1- (6ΣD²)

    n(n<sup>2</sup>-1)

Question 8

How to interpret r_s?

Answer 8

Magnitude, direction, form, outliers & unusual features

Question 9

Formula for line of regression

Answer 9

y_hat=bx+a

b = r(S_y/Sx)

a=y_bar+ bx_bar

S = square root(Σ(x-x_bar)/(n-1)

Question 10

What is another name for IV?

Answer 10

predictor

Question 11

What is another name for DV?

Answer 11

criterion

Question 12

What does r² give?

Answer 12

The amount of variance in Y (DV) accounted for in X (IV)

Question 13

Formulae for r²?

Answer 13

r² in simple regression

SSerror _ = Σ(Yi-Y_hat)²_

SStotal = Σ(Y_i-Y_bar)²

SS_{regression =}Σ(Y_hat-Y_bar)²

SS_totalΣ(Y_i-Y_bar)²

Question 14

Problems with linear regression?

Answer 14

Multicollinearity, heteroscedasticity, outliers, and extrapolation

Question 15

What’s wrong with multicollinearity?

Answer 15

Variance is accounted for twice and not all of it is considered

Question 16

What’s wrong with heteroscedasticity?

Answer 16

Assume a normal distribution, but it’s not…

Question 17

What’s wrong with outliers?

Answer 17

They weigh the R and give an invalid depiction of the sample

Question 18

What’s wrong with extrapolation?

Answer 18

Not accurate

Question 19

What’s a moderator?

Answer 19

Moderators are 3rd variables that explain WHEN a relationship occurs (nominal variables, like gender, height)

Question 20

How do you test for moderation?

Answer 20

Run regression for interaction term (IVxmoderator) and if sig is <.05, then there’s moderation (code moderator = 0)

Question 21

What is a mediator?

Answer 21

3rd variable that explains WHY there’s a relationship between predictor and criterion

Question 22

How to test for mediator?

Answer 22

Run regression between interaction term (IVxmoderator);

if standardized beta coefficient of c’ decreases, then there’s moderation

Question 23

What is reliability?

Answer 23

Consistency in data and ability to reproduce the data

Question 24

5 ways to test reliability?

Answer 24

1. Test, Re-test reliability
2. Alternate Forms reliability
3. Split Half reliability
4. Inter-rater Reliability
5. Internal Consistency

Question 25

What is test, retest reliability?

Answer 25

Test, then test again later

May induce practice effects :(

Question 26

What is alternate forms reliability?

Answer 26

Test and test again with different & equivalent test

Question 27

What is split-half reliability?

Answer 27

Run regression between 2 halves of tests (odds and evens, first and last part)

Question 28

What is inter-rater reliability?

Answer 28

Regression between judges and their scores (uses intraclass consistency)

subj. variability/subj. variability + error

0 = no reliability

1 = reliability

Question 29

What is internal consistency?

Answer 29

Regression among similar questions; treat each question as a separate test; use cronbach’s alpha

Question 30

What is cronbach’s alpha?

Answer 30

how well each item correlates with each other

Question 31

What is validity?

Answer 31

truth in measurement; accurately measuring what you intend to measure

Question 32

construct validity

Answer 32

how measuring device accurately measures target construct:

1. concurrent validity
2. discriminant validity

Question 33

concurrent validity

Answer 33

test correlation between two similar constructs; high correlation = good

Question 34

discriminant validity

Answer 34

run correlation between two opposite tests of different constructs; low correlation is good

Question 35

criterion validity

Answer 35

how well the test measures outcome external of measuring device:
1. predictive validity

2. postdictive validity
3. concurrent validity

Question 36

predictive validity

Answer 36

how well the test predicts future actions

Question 37

concurrent validity

Answer 37

two tests taken at same time to predict behavior

Question 38

postdictive validity

Answer 38

how well the test measures behavior after occurence: known groups paradigm