Exam 1

Question 1

Know the procedures involved in hypothesis testing, null and alternative hypotheses,
alpha levels, decision rule (reject/retain), directional (one sided) vs. nondirectional (two
sided) tests, etc.

Question 2

What are the steps for testing the null hypothesis?

Answer 2

Step 1: State the null hypothesis
Step 2: State the alternative (experimental) hypothesis
Step 3: Set the alpha (significance) level: a = .05 (or a = .01)
Step 4: Set the Rejection Rule
Step 5: Compute your statistic
Step 6: Decision

Question 3

What are the differences between Type I and Type II errors. What is their relationship to
the alpha level (e.g., how does decreasing alpha from .05 to .01 affect the likelihood of
Type I and Type II errors?)

Answer 3

Type I error occurs when there is a false alarm. We mistakenly conclude that our independent variable had an effect on our dependent variable, when in reality these two variables were NOT related.

Type II error occurs when there is a miss. We mistakenly conclude that our independent variable had no effect on our dependent variable, but in reality it actually did have an effect.

Question 4

Know about between-subject designs and within-subject/repeated measures designs.

Answer 4

Between-subjects design:
Each participant has equal probability of assignment to any one of the experiment conditions; confounds minimized using random assignment.

Within-subjects design:
Each participant engages in every experimental condition multiple times; confounds are minimized by counterbalancing.

Question 5

What are the advantages and disadvantages of within subjects designs?

Answer 5

Advantages of Within-Subjects Design:
Create more equivalent groups at experiment onset (controls for individual differences)
Increases power (reduces random error)
Need fewer participants
Less total time required for the experiment
Required to investigate certain research questions or unique populations

Disadvantages of Within-Subjects Design:
Order effects - occur when participants are affected by the order in which they encounter conditions (confounding variable)
Practice Effects:
Participants do better because they do the act repeatedly, resulting in better performance.
Difference due to IV. The difference is from something that we

Fatigue Effects
Participants get tired of doing tasks, resulting in worse performance.

Treatment Carryover Effects

Sensitization
The more you expose someone to an experimental situation
The more likely they are going to figure out what they are looking for

Question 6

What are advantages and disadvantages of between subjects designs?(characteristics, advantages, disadvantages, etc.)

Answer 6

Advantages of Between-Subjects Designs
No carryover effects
Less likely that participants will catch on to the hypothesis
Exposure to multiple levels of the IV may be impossible or ethically and practically difficult

Disadvantages of Between-Subjects Designs
Different people in each condition generate more variability. Making it more difficult to establish an effect of the IV on the DV
More participants required
Anytime you go with between-subjects designs requires more participants.

Between subjects takes twice as much time as within-subjects design.

Question 7

What is statistical power is and how do you improve it?

Answer 7

• What is statistical power is and how do you improve it?
  Statistical Power: What is it, and how can you boost it?
  Power is your ability to find a statistically significant difference between your experimental conditions.

Two ways to boost your power:
Reduce Random Error
Increase treatment effect

Easiest way to boost power is to focus on number 2, don’t worry about number 1

Question 8

Know examples of the order effect and how to overcome these problems

Answer 8

Order effects - occur when participants are affected by the order in which they encounter conditions (confounding variable)
Practice Effects:
Participants do better because they do the act repeatedly, resulting in better performance.
Difference due to IV. The difference is from something that we
Fatigue Effects
Participants get tired of doing tasks, resulting in worse performance.
Treatment Carryover Effects
Sensitization
The more you expose someone to an experimental situation
The more likely they are going to figure out what they are looking for

Question 9

Know what counterbalancing is and the two types discussed in class (ABBA vs. block
randomization)

Answer 9

Participants are assigned to a specific sequences of conditions to ensure that potential order effects will counterbalance themselves and not bias any effect that is due to the IV.

Two types of Counterbalancing
ABBA Counterbalancing
Block Randomization

ABBA Counterbalancing
12344321 or 24311342 or 43211234

The number is the condition
The color is the order.

Block Randomization
For each participant, we are going to run them through a block of all the conditions we are testing. There are 4 conditions. Each condition is a letter.
All of the conditions will be exposed to all those in the block.
The order of the conditions is randomized.

It is much more involved
It takes a lot longer for the participant
Much more effective with counterbalancing things

Question 10

What is the difference between a single factor multi-level design and a factorial design?
When do you use each?

Answer 10

Single-factor, Multilevel design
has only one IV; IV must have more than two levels of IV

Question 11

What is the advantage of conducting a one-way ANOVA vs. multiple t-tests?

Answer 11

ANOVA - Analysis of Variance
Used when you have a single IV (factor with 3 or more conditions.
Primary advantage over running multiple t-tests is that it avoids alpha inflation (the increased chance of making a Type I error when running multiple t-tests)

Question 12

What 3 things can account for between-group variability? What 2 things can account for
within-group variability? What happens to your F-ratio as your treatment effect
Increases?

Answer 12

BG Variability:
Treatment
Individual differences
Experimental Error
In all likelihood. Its all three combined.

WG Variability
Individual differences
Error

Question 13

What are the advantages and disadvantages of using a factorial design?

Answer 13

Factorial designs are better able to capture real-life causal complexity than are designs that manipulate only one IV.

In a between-subjects factorial design, each participant experiences only one condition.

In a within-subjects factorial design, each participant experiences every condition.

Mixed-factorial designs include one or more between-subjects variable and one or more within-subjects variable.

Question 14

Know how to describe a factorial design based on the number of variables and the
number of levels of each

Answer 14

Example:
I used a 2 (Factor A) x 3 (Factor B) design.

Question 15

Know the difference between a main effect and an interaction in a factorial ANOVA

Answer 15

Main effect - you isolate each IV by itself and are looking to see if that had an effect
Each IV has a significant effect on the dependent variable by itself (e.g., Factor A averaged across levels of Factor B)

Establish interaction
Effect of IV on DV depends on level of another IV (the combined effects of multiple IVs)

Question 16

Know how to calculate a main effect using marginal means and how to interpret an
interaction on a graph

Answer 16

Marginal Means: to calculate the marginal mean you simply add the numbers in each of the rows in the matrix horizontally and the numbers in each of the columns vertically. If the sums in the rows are different there IS an interaction. If the sums in the columns are different, there IS an interaction.

Question 17

What is a post hoc test? When is it appropriate to use? What does it tell you?

Answer 17

A post hoc test is performed to show where the difference in the results is. This test is appropriate when there are three or more groups.

Question 18

What is a single case experimental design?

Answer 18

Researchers systematically examine how an IV influences the behavior of an individual case (e.g., an individual client in the Meredith Autism Program).

Question 19

What are the key features of a single-case experimental design? How does it address
the 3 criteria for establishing causality?

Answer 19

Each participant serves as his/her own control (baseline phase) or comparison (treatment phase)
DV is measured across multiple traits
Built-in replication
Data examined separately for each participant (not combined as a group)
Reliance on visual analysis of data (i.e., no SPSS statistics required)

Three conditions that must occur in order to determine causality:
Covariation of events
When A changes, then B must change

Time - order relationship
A must come before B.

Eliminate plausible alternative explanations.

Question 20

Know the characteristics of and differences between an ABAB (reversal) design, a
multiple-baseline design, and a changing criterion design

Answer 20

Sequence of phases in which treatment is either absent or present
Typically, treatment absent during “A” phase (called baseline phase) and present during “B” phase (called a treatment phase)
Often called withdrawal or reversal designs as the second A phase often entails withdrawal of treatment

Behavior measured repeatedly during a baseline period and then during a treatment period

Some sort of replication is conducted

Timing of treatment is varied to rule out alternative explanations
(e.g. confounding variables)

But watch out for contamination

Initial baseline phase followed by a treatment phase

When target behavior reaches a certain threshold, a new performance criterion is set

You hope to wean them off entirely so that the motivation eventually becomes intrinsic.

Question 21

You will need to understand when to use a particular statistic when provided with a
particular scenario/design (i.e., “When to Use What” chart)

Question 22

What is the difference between directional and nondirectional tests?