QUIZ 9 1) An independent variable that cannot be randomly assigned is called aA) Control variableB) Natural treatment variableC) Dependent variableD) All of the above2) An experiment that manipulates two or more independent variables is referred to as a _______________designA) Between-subjectsB) Within-subjectsC) Single-factorialD) Multifactorial3) Your best bet to establish that the independent variable causes changes in the dependent variable.A) Latin-squares designB) Quasi experiment C) Within-subjects designD) True experiment4) What is the difference between a single-factor design and a multi-factorial design?A) A single-factor design is non-experimental whereas a multi-factorial is experimental.B) A single-factor design is experimental whereas a multi-factorial design is non- experimental.C) A single-factor design has one independent variable whereas as a multi-factorial design has two or more independent variables.D) A single-factor design has one dependent variable whereas as a multi-factorial design has two or more dependent variables.5) Experimental control ideally produces groups that are identical except for theirexperience withA) The independent variableB) The dependent variableC) Unmeasured variablesD) The confounding variable6) This is a characteristic unique to true experiments.A) Independent variableB) Dependent variableC) Control variableD) Random assignment7) In experiments, independent variables are often referred to asA) Extraneous variables B) ConfoundsC) FactorsD) Variances8) Tyler presents each participant with a gift of $5, $10, or $15 and then he measures his participants’ generosity in a subsequent task. This study is best described as a ______.A) within-subjects single-factor experimentB) between-subjects single-factor experimentC) within-subjects multifactorial experimentD) between-subjects multifactorial experiment9) In _____ designs, participants experience each level of the ___ variable.A) Between-subjects; independentB) Between-subjects; dependent C) Within-subjects; independentD) Within-subjects; dependent10) In ________ designs, experimental error comes from _____, when experiencing one condition affects the experience of another condition.A) Between-subjects; individual differencesB) Between-subjects; carryover effectsC) Within-subjects; individual differencesD) Within-subjects; carryover effects11) Internal validity most directly speaks to a researcher’s ability to A) Generalize a study’s findings B) Publicize a study’s findings C) Attribute scores on the dependent variable to the effect of the independent variableD) Attribute scores on the independent variable to the effect of the dependent variable12) Adams and Kleck (2003) manipulated emotional expression (anger/fear) and gaze direction (direct/averted) of faces. All participants made speeded judgments as to whether the face displayed anger or fear. What is the correct notation for the factorial design used in this study?A) 2 x 4B) 4 x 2C) 3 x 3D) 2 x 213) Adams and Kleck (2003) manipulated emotional expression (anger/fear) and gaze direction (direct/averted) of faces. All participants made speeded judgments as to whether the face displayed anger or fear. What is the dependent variable?A) Speeded judgment B) Emotional ExpressionC) Gaze DirectionD) Anger faces14) Adams and Kleck (2003) manipulated emotional expression (anger/fear) and gaze direction (direct/averted) of faces. All participants made speeded judgments as to whether the face displayed anger or fear. What are the independent variables?A) Anger faces, Speeded JudgmentB) Emotional expression, Gaze DirectionC) Fear faces, Speeded JudgmentD) All of the above15) What were the main effects tested in the Adams and Kleck (2003) study?A) Emotional Expression, Gaze DirectionB) Gaze Direction, Speeded JudgmentC) Emotional Expression, Speeded JudgmentD) All of the above 16) If in the Adams and Kleck (2003) study, participants had their fastest response times for anger faces than for fear faces regardless of gaze direction, this would mean that the results showed a: A) Main effect for emotion expressionB) Main effect for gaze directionC) Main effect or speeded judgment D) All of the above17) If in the Adams and Kleck (2003) study, participants had their fastest response times for faces with direct eye gaze than for faces with averted eye gaze, regardless of emotional expression, this would mean that the results showed a: A) Main effect for emotion expressionB) Main effect for gaze directionC) Main effect or speeded judgment D) All of the above18) If in the Adams and Kleck (2003) study, participants had their fastest response times for anger faces with direct eye gaze, this would mean that the results showed ——————– interaction A) Emotional Expression X Speeded JudgmentB) Gaze Direction X Speeded JudgmentC) Emotional Expression X Gaze DirectionD) Emotional Expression X Eye Test19) You test a main effect for each _________variable.A) ControlB) Dependent C) IndependentD) Intervening20) In a 2x2x3 design, there are _______ conditions.A) 12B) 3C) 6D) 921) In a 2×2 design, you test for _______ interaction(s).A) 1B) 0C) 2D) 422) _______ interaction(s) can be a tested in a single-factor experiment. A) OneB) TwoC) ZeroD) Three23) Julie uses a within-subjects design to study the effects of caffeine (none or 8 ounces of coffee) and exercise (none or 10 min of jogging) on cognitive performance. How many groups of participants will she need?A) OneB) TwoC) FourD) Six24) Compared to a between-subjects approach, a within-subjects multifactorial experimental design ______.A) is more costlyB) is more affected individual differencesC) requires fewer participantsD) is less affected by carryover effects25) Bill is studying how individuals’ ability to concentrate is affected by both music type (pop vs. classical) and volume (soft vs. loud). If he finds that concentration is best when classical music is played softly this will be referred to as a(n) ______.A) interactionB) factorial effectC) main effectD) 2 ´ 2 effect26) Bill is studying how individuals’ ability to concentrate is affected by both music type (pop vs. classical) and volume (soft vs. loud). If he finds that concentration is best with classical music regardless of whether played softly or loudly this will be referred to as a(n) ______.A) interactionB) factorial effectC) main effectD) 2 ´ 2 effect**textbook:Research Methods in Psychology: Investigating Human Behavior Front Cover Paul G. Nestor, Russell K. Schutt
_sp_chapter_9_10.ppt
sp_20_anova_update_chapter_10_revised.ppt
ch8_review.ppt
sp_20_ch8.ppt
spring20_ch7_8.ppt
Unformatted Attachment Preview
True Experiments Use Random
Assignment
Random Assignment: Leveling the
Playing Field
Random assignment acts to “level the
playing field” before the application of the
independent variable.
Stamps out selection bias (sort of)
Design Experiment To Reduce
Chance Variation
Difference between groups on the dependent
variable can be attributed to the direct
manipulation of the independent
Such a difference that is unlikely to be due to
chance is “statistically significant.”
Two Design Options in Assigning
Participants
independent-groups design also known as a
between-subjects design
independent-groups, between-subjects design
repeated-measures design, also known as a
within-subjects design
repeated measures, within-subjects design
Independent-Groups, BetweenSubjects Design
Participants are randomly assigned to each of the
experimental conditions.
Each participant in each group experiences only one
condition of the independent variable.
Independent-groups,between-subjects designs require a
large number of people to be enrolled in a study.
Independent-Groups Design
Repeated –Measures, WithinSubjects Design
A repeated-measures design compares the
performance of the same individual across
all of the different experimental
conditions.
When individuals are presumed to vary
widely on a dependent variable, a
repeated-measures design is often the
preferred choice for testing a research
hypothesis.
Major Limitation of Repeated-Measures,
Within-Subjects Design: Carryover Effects
An important source of experimental error
for a repeated-measures, within-subjects
design.
Carryover Effects Are Controlled By
Counterbalancing
Randomizing the order in which participants
receive treatments is a way to combat carryover
effects.
Counterbalance the order of treatments
Controlling for Carryover Effects in
Repeated Measures Design
A technique to control for the order of treatments
is counterbalancing.
Counterbalancing the order of treatments tends
to be more effective than randomizing the order
of treatments because it ensures that each
treatment or level of the independent variable
occurs in each time period of the experiment.
That way, every treatment has the same chance
of being influenced by confounding variables
related to a treatment coming before and after it.
Repeated Measures: Counterbalancing
Order of Treatment
Within-Subjects Design (Repeated
Measures)
Counter Balance with a Latin Square
Design
With complete counterbalancing often
untenable, researchers will frequently use
what is called a Latin-square design as
a way to combat confounds of carryover
effects in within-subjects experiments.
A Latin-square design is an incomplete
counterbalancing arrangement in which
each possible order of treatments occurs
equally often across research participants.
Between or Within?
To manipulate an independent variable
between-subjects or within-subjects?
That is the question, what is the answer?
Go with “Between” when….
Want to neutralize individual differences
and groups will equal prior to treatment or
manipulation of the independent variable,
such
Drug outcome study, such as Randomized
Clinical Trial.
Between or Within?
To manipulate an independent variable
between-subjects or within-subjects?
That is the question, what is the answer?
Go with “Within” when..
Carryover effects are not a huge problem
and counterbalancing of the order of
presentation is easy…
NULL HYPOTHESIS SIGNIFICANCE
TESTING
Statistical significance is used to test what
is referred to as the null hypothesis.
The null hypothesis is defined as the
hypothesis of no difference or no
relationship, which the researcher tries to
reject, nullify, or disprove.
The research hypothesis, predicts a
specific relationship between the
independent variable and dependent
variable
Statistical Significance
Are the results of an experiment
statistically significant?
To answer this question, inferential
statistics provide a test of statistical
significance.
Statistical Significance and
Probability Values
Statistical significance testing tells us the
likelihood or probability that the observed
effect revealed by data analysis could be
due to chance alone.
Statistical probabilities are set at levels of
significance in the form of probability (p)values
Statistical Significance= p<.05
Traditionally, p-values of .05 or less
indicate that an obtained finding is
statistically significant, meaning that there
is a 5% chance or less that the obtained
results are due to chance alone.
Statistical significance simply means that
a finding is unlikely due to chance at a
certain level of probability, usually .05 or
less.
Statistical Significance and Null
Hypothesis
The null hypothesis is defined as the
hypothesis of no difference or no
relationship, which the researcher tries to
reject, nullify, or disprove.
A statistically significant result allows you
to reject the null hypothesis
Statistical Significance and
Research Hypothesis
The research hypothesis predicts a
specific relationship between the
independent variable and dependent
variable
If our statistical analysis allows us to
reject the null hypothesis, then the
research hypothesis is accepted.
Type I and II Errors
Two types of errors must be weighed in
making decisions about whether to reject
or accept the null hypothesis.
◼
◼
Type I
Type II
Type I Error
Type I error occurs when the null
hypothesis is wrongly rejected.
What is the likelihood of a Type I error,
that is, rejecting the null hypothesis when
in fact it is true?
The answer is the level of statistical
significance stated as a probability (i.e., pvalue).
Probability of a Type I error is the
significance level
Type II Error
Type II error occurs when the null
hypothesis is incorrectly accepted.
You have missed a significant result
because your research design lacked
sensitivity.
Type II errors are typically understood as
a problem of statistical power, which as
you know means the extent to which a
study is adequately designed to find the
predicted significant effect
Type I and II Errors: Internal
Validity
How might Type I and Type II errors bear upon
the internal validity of an experiment?
A Type I error may occur because of a design
flaw, for example, a failure to randomize the
order of stimulus presentation in a test of
memory of high imagery words.
Type II errors are typically understood as a
problem of statistical power, which as you know
means the extent to which a study is adequately
designed to find the predicted significant effect
Statistical Power and Type II
Error
Type II errors are typically understood as
a problem of statistical power, which as
you know means the extent to which a
study is adequately designed to find the
predicted significant effect.
The likelihood of a Type II error decreases
as internal validity of an experiment
increases.
Internal Validity and Statistical
Power
As internal validity of an experiment
increases, so does its statistical power.
Larger samples provide greater statistical
power.
The idea is that if only a handful of
research participants are tested, then a
negative finding of no difference or no
relationship may arise simply because not
enough people were tested.
Reproducibility and Replication
Reproducibility is a core principle of the
scientific method.
A direct replication of an experiment
attempts to recreate the conditions of the
research design believed to be sufficient
for obtaining the previously reported
finding.
If the same results are generated by the
new, independent investigation, then we
can say that the experiment has been
successfully replicated.
Single -Factor Experiment
Oxytocin Improves “Mind-Reading” in
Humans
What is the independent variable?
◼
Treatment (oxytocin, placebo)
What is the dependent variable
◼
Scores on the RMET
Single-Factor Design
→Multifactorial Design?
How and why?
Remember factor = independent variable
Simplest Multifactorial Design?
2 x 2 Design
2 Independent variables, each with 2
levels
Notations and Terms
The simplest multifactorial experimental
design contains two independent
variables, each with two levels or values.
This known as a 2 x 2 design
Factorial experiments are typically
designated or identified by a numbering
notation.
Notation
A 2 × 2 factorial design has two independent variables,
with two levels or values.
The number of numbers tells how many factors or
independent variables there are, and the number
values indicate the number of levels of the
independent variables.
A 3 × 4 (spoken as “three-by-four”) factorial design
indicates two independent variables, one with three levels,
and the other with four levels.
The order of the numbers makes no difference, so that a 3
× 4 factorial design could be just as easily identified as a 4
× 3.
Combining Levels of Independent
Variables in Multifactorial Designs
In a factorial design, every level of each
independent variable is combined.
For a 2 x 2 design, the two levels of each
independent variable are combined for a total 4
levels/conditions/treatments.
For a 3 × 4 design, this means the three levels of
one independent variable are combined with the
four levels of the other independent variable for a
total of 12 levels or treatments.
Calculating levels/conditions/treatments in a
multifactorial design?
The number of treatment
groups/conditions/levels that we have in any
factorial design can be calculated by simply
multiplying through the number notation.
In a 2 × 2 example, we have 2 × 2 = 4 groups.
In a 3 × 4 factorial design, we have 3 × 4 = 12
groups.
A factorial experiment allows us to examine all
these combinations.
Research Idea
You want to design an experiment that
looks at how fast people recognize facial
expression of emotion.
So your dependent variable will be
reaction time ----how quickly to recognize
a facial expression of emotion.
You will have 2 independent variables,
each with two levels.
Research Idea
You want to design an experiment that
looks at how fast people recognize facial
expression of emotion.
So your dependent variable will be
reaction time ----how quickly to recognize
a facial expression of emotion.
You will have 2 independent variables,
each with two levels.
Name that emotion
Name that emotion
What is manipulated?
Anger
Fear
What is manipulated?
Direct Eye Gaze
Averted Eye Gaze
Experimental Stimuli
Researchers created experimental stimuli
by constructing faces that varied in
emotional expression and eye gaze
direction.
2 x 2=4 conditions or 4 types of faces
◼
◼
◼
◼
1)
2)
3)
4)
anger with direct gaze
anger with averted gaze
fear with direct gaze
fear with averted gaze
Two Independent Variables
Emotional Expression
Anger
Fear
Eye Gaze Direction
Direct
Averted
2 X 2: Emotional Expression and
Eye Gaze
Quick Check:
In a 3 x 4 x 2 multifactorial design, there
are:
A) Two independent variables
B) Three independent variables
C) Four independent variables
D) Six independent variables
Factorial Design: 2 Independent
Variables
2x2
IV1: EMOTIONAL EXPRESSION (ANGER,
FEAR)
IV2: EYE GAZE (DIRECT, AVERTED)
DV: REACTION TIME
Experimental Task:
Participants viewed, one at a time, on a computer
monitor, a face that had an expression that had
either anger or fear and a gaze direction of
either direct or averted.
For each face, participants made a speedy
judgment as to whether the face displayed anger
or fear by responding via a right or left mouse
click.
Participants were instructed to label each face
(fear/anger) as quickly and accurately as
possible.
Their 2 x 2 Produces
4 conditions
2 x 2 Table
Direction of Eye Gaze (A)
(Independent variable A)
Row Mean
(Main Effect of Emotional Expression
Type of Emotional Expression (B) (Independent variable B)
Direct (A1)
Averted (A2)
Anger (B1)
862.3 A1B1
914.1 A2B1
888.2
Fear (B2)
944.5 A1B2
891.2 A2B2
917.9
903.4
902.7
Column Means (Main Effect of
Gaze Direction)
2 Independent Variables; 1 Control
Variable
Photographs differ on two important features.
These two important features are: (1) emotional expression
and (2) direction of eye gaze.
Each is an independent variable, each with two levels
Emotional Expression
◼
◼
Direction of Eye Gaze
◼
◼
Anger
Fear
Direct
Averted
Actual identity of the person is the same in both
photographs. Identity is therefore a control variable that is
held constant across both photographs.
Multifactorial Designs
Two or more independent variables are
manipulated at the same time within the
same study.
These experimental designs can become
quite complex.
Referred to as factorial designs.
We use the term multifactorial for
experiments that vary two or more
independent variables.
2 Major Advantages of Multifactorial
Designs
First, with a multifactorial experiment, the effects
of each independent variable on the dependent
variable can be isolated and tested.
Second, a multifactorial experiment allows the
researcher to isolate and test what are referred
to as the interaction effects of the independent
variables on the dependent variable.
As such, multifactorial experiments provide a
powerful and economical research design to
begin to disentangle the intricacies of human
experience.
Newsflash: Interaction, New
Concept, Must Know
An analogy might be helpful.
Different drugs are known to interact to produce
harmful or beneficial effects.
Valium and alcohol when taken together, can
interact to produce feelings of depression.
Using each alone, however, may produce a very
different emotional effect.
Two drugs may work together or synergistically
to enhance or magnify one or more effects.
Elements interact to generate effects that
otherwise would not have occurred with each
drug alone.
Interaction in Multifactorial
Experiment
Look at the four photographs below that
vary on two factors, emotional expression
and eye gaze direction.
Let’s say we found that emotional
expression and eye gaze direction
interacted to influence our responses to
these photographs.
What could this mean?
What does interaction mean?
Let’s say we found that emotional
expression and eye gaze direction
interacted to influence our responses to
these photographs.
Let’s say we found that emotional
expression and eye gaze direction
interacted to influence our responses to
these photographs
No Interactions Can be Tested in
Single Factor Experiment. Why?
Say we had a single-factor experiment
with only one independent variable,
emotional expression, and we found faster
response to anger than fear faces.
But now in our multifactorial experiment,
we add a second independent variable,
eye gaze direction.
Need two or more independent variables
to test interaction
Quick Check
) An experiment that manipulates two or
more independent variables is referred to
as a _______________design
A) Between-subjects
B) Within-subjects
C) Single-factorial
D) Multifactorial
Quick Check
A researcher chooses a single-factorial design:
A) To examine the effects of two or more
independent variables on a dependent
variable
B) To examine the effects of one independent
variable on a dependent variable
C) To examine the effects of the interaction of
the independent variable on the
dependent variable
D) All of the above
Quick Check
A researcher chooses a multifactorial design:
A) To examine the effects of two or more
independent variables on a dependent
variable
B) To examine the effects of one independent
variable on a dependent variable
C) To examine the effects of the correlation of
the independent variable and the
dependent variable
D) All of the above
Quick Check
What is the difference between adding a level to
an independent variable versus adding a new
independent variable?
A) The new independent variable must have only
one level.
B) The old independent variable must have only
one level.
C) The new independent variable must be varied
between subjects.
D) The two independent variables are
qualitatively different from each other
Quick Check
Why is a multifactorial experiment more economical and efficient
than a single-factorial experiment?
A)
Instead of running a separate single-factorial experiment for
each independent variable, you can test the effects of two or more
independent variables in a multifactorial experiment.
B) Instead of running a separate, single-factorial experiment for
each dependent variable, you can test the effects of two or more
dependent variables in a multifactorial experiment.
C) Instead of running a separate, single-factorial experiment for
each control variable, you can test the effects of two or more
control variables in a multifactorial experiment.
D) All of the above
Quick Check:
In a 2 x 3 x 2 multifactorial design, there
is:
A) A total of four conditions
B) A total of six conditions
C) A total of twelve conditions
D) None of the above
Quick Check:
In a 2 x 3 factorial design,
A) One dependent variable has two levels, and
the other dependent variable has three levels
B) One independent variable has six levels.
C) One independent has three levels, and the
other independent variable has two levels.
D) Three independent variables, each with two
levels.
NULL HYPOTHESIS SIGNIFICANCE
TESTING
Statistical significance is used to test what
is referred to as the null hypothesis.
The null hypothesis is defined as the
hypothesis of no difference or no
relationship, which the researcher tries to
reject, nullify, or disprove.
The research hypothesis, predicts a
specific relationship between the
independent variable and dependent
variable
Statistical Significance
Are the results of an experiment
statistically significant?
To answer this question, inferential
statistics provide a test of statistical
significance.
Statistical Significance and
Probability Values
Statistical significance testing tells us the
likelihood or probability that the observed
effect revealed by data analysis could be
due to chance alone.
Statistical probabilities are set at levels of
significance in the form of probability (p)values
Statistical Significance= p<.05
Traditionally, p-values of .05 or less
indicate that an obtained finding is
statistically significant, meaning that there
is a 5% chance or less that the obtained
results are due to chance alone.
Statistical significance simply means that
a finding is unlikely due to chance at a
certain level of probability, usually .05 or
less.
Statistical Significance and Null
Hypothesis
The null hypothesis is defined as the
hypothesis of no difference or no
relationship, which the researcher tries to
reject, nullify, or disprove.
A statistically significant result allows you
to reject the null hypothesis
Statistical Significance and
Research Hypothesis
The research hypothesis predicts a
specific relationship between the
independent variable and dependent
variable
If our statistical analysis allows us to
reject the null hypothesis, then the
research hypothesis is accepted.
Type I and II Errors
Two types of errors must be weighed in
making decisions about whether to reject
or accept the null hypothesis.
◼
◼
Type I
Type II
Type I Error
Type I error occurs when the null
hypothesis is wrongly rejec ...
Purchase answer to see full
attachment
Why Choose Us
- 100% non-plagiarized Papers
- 24/7 /365 Service Available
- Affordable Prices
- Any Paper, Urgency, and Subject
- Will complete your papers in 6 hours
- On-time Delivery
- Money-back and Privacy guarantees
- Unlimited Amendments upon request
- Satisfaction guarantee
How it Works
- Click on the “Place Order” tab at the top menu or “Order Now” icon at the bottom and a new page will appear with an order form to be filled.
- Fill in your paper’s requirements in the "PAPER DETAILS" section.
- Fill in your paper’s academic level, deadline, and the required number of pages from the drop-down menus.
- Click “CREATE ACCOUNT & SIGN IN” to enter your registration details and get an account with us for record-keeping and then, click on “PROCEED TO CHECKOUT” at the bottom of the page.
- From there, the payment sections will show, follow the guided payment process and your order will be available for our writing team to work on it.