Exam 3 Material

Question 1

What are bivariate correlations?

Answer 1

composed of 2 variables
used to determine the relationship between two different variables

Question 2

What type of variables are found in bivariate correlations?

Answer 2

measured variables
1 = continuous
the other may be continuous or categorical
the variables must have greater than or equal to 2 levels

Question 3

What are 3 limitations to correlational research?

Answer 3

1. can’t randomly assign
2. prediction as primary goal
3. can’t manipulate

Question 4

What is a construct validity concern with correlations?

Answer 4

How well was each variable measured?

Question 5

What is a statistical validity concern with correlations?

Answer 5

How well do the data support the state conclusions?

Question 6

What is the relationship between statistical significance and effect size?

Answer 6

Larger effects + larger sample size –> significant p-value
large samples are needed to get sig effects with the effect size is small

Question 7

What are the implications of larger effect sizes for correlations?

Answer 7

more accurate predictions based on correlation

Question 8

What are the two types of effect sizes?

Answer 8

R - 2 continuous variables
d - 2 variables, 1 is categorical

Question 9

What does measurement error influence?

Answer 9

Reliability
unreliability reduces the observed correlation

Question 10

How does restriction of range influence correlations?

Answer 10

It distort observed correlations
gives a biased estimate

Question 11

What are the two types of restrictions of range?

Answer 11

the ceiling effect
the floor effect

Question 12

What is desirable variability vs. undesirable variability?

Answer 12

Desired: we want variability in X and Y

Question 13

What are 5 statistical validity concerns?

Answer 13

Effect size
significance testing
measurement error
restriction of range
outliers

Question 14

What are the 3 criteria for causation?

Answer 14

Covariance
Temporal Precedence
Internal Validity

Question 15

are multivariate associations better than bivariate?

Answer 15

not necessarily, but the do “get closer” to causal inferences

Question 16

What are the 3 types of longitudinal correlations?

Answer 16

Cross-sectional
Autocorrelations
Cross-lag

Question 17

What are cross-sectional correlations?

Answer 17

aka synchronous
time 1 is compared to variable A
time 2 is compared to variable B

Question 18

What are autocorrelations?

Answer 18

aka stability
time 1 is compared to time 2
variable a is compared with variable b

Question 19

What are cross-lag correlations?

Answer 19

time 1 is compared to variable b
time 2 is compare to variable a
tells us which came first
1 sig correlations shows directionality

Question 20

What criteria for causality does multiple regression address?

Answer 20

internal validity
rules out 3rd variables

Question 21

What types of variables are in a multiple regression?

Answer 21

predictor variables (>2)
outcome variables (1)

Question 22

What is the effect size used in regression?

Answer 22

Hierarchical multiple regression: each steps adds a simultaneous regression

Question 23

What is R^2?

Answer 23

coefficient of multiple determination
how close the data are to the fitted regression
% of outcome variable variance that is explained by the model

Question 24

What is pattern and parsimony?

Answer 24

the results of a variety of correlational studies all support a single, causal theory
or
the most parsimonious explanation for a pattern of results across studies is a causal one

Question 25

What is mediation?

Answer 25

WHY 2 variables are associated implies causation

Question 26

What is moderation?

Answer 26

WHEN or FOR WHOM are two variables associated

Question 27

a moderator...

Answer 27

...influence the relationship between 2 variables x <--------->y ^ moderator EXTERNAL VALIDITY

Question 28

a mediator...

Answer 28

... explains the relationship between 2 variables x ---> mediator --> y INTERNAL VALIDITY

Question 29

What is full or partial mediation?

Answer 29

full: after considering the mediator variable, there is no x or y relationship partial: some relationship exists between x and y without mediator variable

Question 30

What is a spurious correlation?

Answer 30

when two variables appear to be correlated but are not icecream and sunburns

Question 31

What types of variables are in an experiment?

Answer 31

_> 1 manipulated _> 1 measured

Question 32

What are 3 potential threats to repeated-measures design? and how to control

Answer 32

Order effects - counterbalancing demand characteristics design confound - keep everything else constant

Question 33

What is Internal Validity as it related to experiments?

Answer 33

Are there any possible alternative reasons for the change in DV other than the change in IV?

Question 34

What is an example of systematic variability?

Answer 34

a 3rd variable/confound that regularly/consistently covaries with IV

Question 35

What validity is systematic variability concerned with?

Answer 35

Internal validity

Question 36

What are 3 examples of unsystematic variability?

Answer 36

1. measurement error 2. individual differences 3. situational noise

Question 37

What validity is unsystematic variability concerned with?

Answer 37

Statistical validity

Question 38

When you control for unsystematic variability you...

Answer 38

... increase power of the study

Question 39

Why is a manipulation check important?

Answer 39

provides empirical evidence of construct validity of the IV

Question 40

What does a pilot study do?

Answer 40

It confirms effectiveness of manipulation in a simple first study

Question 41

what test is associated with effect size?

Answer 41

Cohen's d

Question 42

What are null effects?

Answer 42

no group/condition difference the IV did not covary with the dv

Question 43

What is the file drawer problems?

Answer 43

when people won't publish studies that find a null effect

Question 44

What are 3 possible reasons for a null effect?

Answer 44

1. IV does not affect DV 2. too much within groups variability 3. too little between groups variability

Question 45

weak manipulations have...?

Answer 45

... less power