You must read each slide, and complete any questions on the slide, in sequence.
Nonexperimental Design
A design in which there is no control or manipulation of the independent variable; cause-and-effect relationships between variables cannot be established.
Experimental Design
A research method in which the experimenter controls and manipulates the independent variable, allowing the establishment of cause-and-effect relationships between the independent and dependent variables.
Independent Variable (IV)
The variable that influences the dependent variable. In experiments, the researcher manipulates or controls this variable.
Dependent Variable (DV)
The variable measured in association with changes in the independent variable; the outcome or effect.
Experimental Group
The group or condition that gets the key treatment in an experiment.
Control Group
Any condition that serves as the comparison group in an experiment.
Empty Control Group
A group that does not receive any form of the treatment and just completes the dependent variable.
Empty Control Group
A group that does not receive any form of the treatment and just completes the dependent variable.
Experimental Realism
The degree to which a study participant becomes engrossed in the manipulation and truly influenced by it.
Mundane Realism
The degree to which a study parallels everyday situations in the real world.
Experimental Control
The ability to keep everything between groups the same except for the one element we want to test in an experiment.
Self-report Measure
Any measurement technique that directly asks the participant how they think or feel.
Behavioral Measure
A measure of participants’ actions in a research design.
Reliability
The stability or consistency of a measure.
Validity
The degree to which a tool measures what it claims to measure.
Sensitivity
The range of data a researcher can gather from a particular instrument.
Experimental Hypothesis
A clear and specific prediction of how the independent variable influences the dependent variable.
Institutional Review Board (IRB)
A board that reviews the ethical merit of all the human research conducted within an institution.
Descriptive
Describes or summarizes what is happening in a meaningful way.
Inferential
Tests a specific prediction about why something occurs.
Multigroup Design
In this activity, you will create a multigroup design in order to test the impact of different body shapes of dolls on body dissatisfaction in girls.
Dr. Melanie Maggard
Dr. Natalie J. Ciarocco, Monmouth University
Dr. David B. Strohmetz, University of West Florida
Dr. Gary W. Lewandowski, Jr., Monmouth University
Something to Think About...
dirk enters/imageBROKER/AGE Fotostock
Scenario: We are constantly exposed to images of unhealthily thin people in the media, through advertisements, film, magazines, and online. These images, whether real or fictional, demonstrate the value our culture places on thinness. Being thin is equated with being beautiful and popular, attributes that girls, in particular, are taught to start valuing at a very young age. Even the toys girls are given—such as dolls with unnaturally thin or unrealistic body types—communicate a cultural pressure to be thin.
Something to Think About...
A Kompatscher/F1online/AGE Fotostock
When girls are taught to compare themselves with others, they might begin to believe that, unlike the celebrities they see on TV or the dolls they play with, they are not thin or pretty enough. How might constant exposure to messages about the “thin ideal” influence young girls? Could dolls with unrealistic body proportions influence how satisfied or dissatisfied girls are with their own bodies? It might be possible that a short amount of time spent playing with these dolls is all that is needed for unrealistic body images to impact how girls view their bodies.
Our Research Question
Jesse Kunerth/iStock/Getty Images
Based on your experiences with or knowledge of dolls that portray an unrealistic body type, you can develop a research study that examines their impact on body dissatisfaction. But first, you will need a framework to help you explore this topic. Research studies all start with a question, so here is your chance to ask one of your own.
Now that you have a research question (“Does exposure to dolls with unrealistically thin body proportions lead to greater body dissatisfaction in girls?”), you must determine which type of research design will best answer your research question. To narrow things down, consider the following:
Now that you know you have an experimental design that compares exposure to unrealistically thin dolls, more realistically proportioned dolls, and no dolls, you can identify your independent and dependent variables.
Because you have an experiment with 1 independent variable and 3 levels (unrealistically thin dolls vs. realistically proportioned dolls vs. no dolls), you have a multigroup design, or experiment with 3 or more groups. Next, we should identify the experimental and control groups.
Next, we need to operationally define the independent variable (IV) of doll type by determining exactly how we will manipulate it. We will want to be sure that our study has a high level of experimental and mundane realism.
It looks like the task that is highest in both experimental and mundane realism involves girls playing with virtual dolls that they are allowed to dress with various outfits and accessories. We know that our experimental group will receive the treatment we are interested in (i.e., the opportunity to dress the unrealistically thin dolls), so now we need to define our control group, keeping in mind the need to maintain experimental control.
You have now established the key comparison between the unrealistically thin dolls vs. realistically proportioned dolls vs. no dolls groups. Next, we need to specify the exact nature of our dependent variable, “body dissatisfaction,” using either a self-report measure or a behavioral measure.
We know we want to use self-report to measure body dissatisfaction. Now it is time to determine which type of self-report measure to use. Consider what could be the ideal number and types of questions, reliability and validity, sensitivity, and appropriateness of the measure for young girls.
Now that you have determined how you will collect your data and your intended sample, you must submit your research procedure to the Institutional Review Board (IRB) for ethical approval. The IRB will determine whether or not your study meets all ethical guidelines.
Institutional Review Board (IRB)
Each IRB has its own protocol that conforms to the national standard when a researcher submits an application for proposed research. In addition to the appropriate paperwork and other information submitted to the IRB, the board considers the following description during their evaluation of your proposed experiment:
The purpose of this research is to determine whether exposure to unrealistically thin dolls leads to higher body dissatisfaction than does exposure to realistically proportioned or no dolls. To study this topic, 8- and 9-year-old girls from a local elementary school will be randomly assigned to an unrealistically thin dolls, realistically-proportioned dolls, or no dolls group. Those in the thin and realistic dolls groups will be presented with and allowed to dress virtual dolls with outfits and accessories for 5 minutes. Researchers will then measure all participants’ body dissatisfaction using a 2–3 minute self-report measure, the Body Parts Dissatisfaction Scale (BPDS).
Responding to the IRB
wk1003mike/Shutterstock
The IRB reviewed your submission and has one concern. Although the study appears to present minimal risk to participants, there is no mention of how informed consent or assent will be obtained for the children in the study.
You must now determine how to respond to the IRB, keeping in mind the ethics of surveying vulnerable populations such as children.
Now that we have secured the IRB’s approval, we should determine what the entire study will look like. Below are the steps of the study. Can you place them in the proper order?
Give participants the Body Parts Dissatisfaction Scale.
Obtain informed consent and verbal assent.
Allow participants in the unrealistically thin doll and realistically proportioned doll groups to dress virtual dolls for 5 minutes.
Debrief the participants.
Give participants instructions for how to dress the virtual dolls if they are in the unrealistically thin doll or realistically proportioned doll groups.
Randomly assign participants to experimental, control, and empty control groups.
Question
HGMMOkn7wGnu8Gj1kWrilkI+/58xQm0QkttXl72EylU8oCrR
Collecting Data
Image Source/Photodisc/Getty Images
Now that you have a sense of how to conduct this study, it is time to see what data from this study might look like.
If you were to run a full version of this study, you would want to have at least 30 participants in each of your three groups, for a total of 90 participants. Because you have a between-subjects design, each participant will only be in one group.
Example Data Set
This is an example of what your data set would look like. The top row shows the variable names; the other rows display the data for the first 10 participants.
In the “Group” column, a 1 = Thin Dolls Group, a 2 = Realistic Dolls Group, and a 3 = No Dolls Group. The Body Parts Dissatisfaction Scale score was recorded under BPDS and represents the number of body parts the participant would like to change to be either smaller or bigger.
Participant Number
Group
BPDS
101
1
6
102
1
6
103
2
2
104
3
1
105
2
1
106
1
5
107
3
2
108
1
4
109
2
2
110
3
2
Selecting the Proper Tool
Ines Koleva/E+/Getty Images
Now that you have collected your data, you must decide the best way to summarize your findings. The decisions you made about how to collect your data dictate the statistics you can use with your data now. First, you need to consider if your study is descriptive or inferential.
The following is an example of output for another three-group design. This study was about how hours slept at night (less than 7 hours, 7–9 hours, and more than 9 hours) influence self-reported happiness.
Before continuing, click on the output to learn more about each of its elements.
Alex Brylov/Shutterstock
To report these numbers in a results section, put the numbers in as follows:
F from some variable equals a number; p equals a number; eta squared equals a number.
F(#,#) = #.##, p = .##, eta2 = .##.
ANOVA
happiness
df
Mean Square
F
Sig.
Between Grops
27.899
2
13.949
30.145
.000
Within Groups
44.424
96
.463
Total
72.323
98
This is the df or degrees of freedom. An ANOVA has two dfs, one for the main effect (between-groups) and one for the error (within-groups).
This is the F statistic. It represents the size of the difference between group means compared to the size of the difference within groups.
This is the p level or the significance level. It represents the probability or likelihood that the results happened by chance. The lower the p level, the less likely the result happened by chance.
The F score and p level will only tell you whether there is a significant difference. To determine which means are different, and the nature or direction of those differences, you need to look at the means via a post-hoc test.
Measures of Association
Eta
Eta Squared
happiness * Condition
.621
.386
The eta squared (eta2 ) is the effect size, it tells us the proportion of change in the dependent variable that is associated with being in the different groups of the independent variable.
The results presented here are from the post-hoc test, which compares each of the groups’ means to all of the other groups’ means.
Question
7NBWBJ9gGmxSPNDcugS1NxEsaZmXxlD8E/M06y/qyjYhbebW
Tutorial: Evaluating Output
Alex Brylov/Shutterstock
Multiple Comparisons
Dependent Variable: happiness
Tukey HSD
(I) Condition
(J) Condition
Mean Difference (I-J)
Std. Error
Sig.
95% Confidence Interval
Lower Bound
Upper Bound
Less than 7 hours sleep
7-9 hours sleep
-1.06061*
.16747
.000
-1.4593
-.6619
More than 9 hours sleep
.12121
.16747
.750
-.2775
.5199
7-9 hours sleep
Less than 7 hours sleep
1.06061*
.16747
.000
.6619
1.4593
More than 9 hours sleep
1.18182*
.16747
.000
.7831
1.5805
More than 9 hours sleep
Less than 7 hours sleep
-.12121
.16747
.750
-.5199
.2775
7-9 hours sleep
-1.18182*
.16747
.000
-1.5805
-.7831
*. The mean difference is significant at the 0.05 level.
This is the difference between the means for those who sleep less than 7 hours
and between 7 and 9 hours.
This is the difference between the means for those who sleep less than 7
hours and more than 9 hours.
This is the difference between the means for those who sleep between 7 and 9
hours and more than 9 hours.
The post-hoc test tells us which comparisons between the means were
significant. The p level tells us the significance level of that comparison.
Those who sleep between 7 and 9 hours are happier than those who sleep less
than 7 hours and those who sleep more than 9 hours.
Those who sleep less than 7 hours and more than 9 hours were not different
but were equally happy.
Those who sleep less than 7 hours and more than 9 hours were not different but
were equally happy.
Descriptive Statistics
Dependent Variable: happiness
Condition
Mean
Std. Deviation
N
Less than 7 hours sleep
3.0303
.80951
33
7-9 hours sleep
4.0909
.72300
33
More than 9 hours sleep
2.9091
.45851
33
Total
3.3434
.85906
99
This is the average or mean (M) happiness rating for those who sleep less
than 7 hours.
This is the standard deviation (SD) of happiness for those who sleep less
than 7 hours.
This is the average or mean (M) happiness rating for those who sleep between
7 and 9 hours.
This is the standard deviation (SD) of happiness for those who sleep between
7 and 9 hours.
This is the average or mean (M) happiness rating for those who sleep more
than 9 hours.
This is the standard deviation (SD) of happiness for those who sleep more
than 9 hours.
In this case the means tell us that those who got 7–9 hours of sleep were
happier than those who got less than 7 hours of sleep and those that got more than 9 hours of sleep. The
results from the post-hoc test support the finding that this group (those who got 7–9 hours of sleep) was
statistically different from the other two groups.
Question
UzyDpBlCm5+2oyCBPDtXpyGbmsyzwmb0g6m+dSuGFsf2rc3V
Your Turn: Evaluating Output
Below is the output from your study:
ANOVA
BPDS
Sum of Squares
df
Mean Square
F
Sig.
Between Groups
256.822
2
128.411
303.306
.000
Within Groups
36.833
87
.423
Total
293.656
89
Measures of Association
Eta
Eta Squared
BPDS * condition
.935
.875
Multiple Comparisons
Dependent Variable: BPDS
Tukey HSD
(I) Condition
(J) Condition
Mean Difference (I-J)
Std. Error
Sig.
95% Confidence Interval
Lower Bound
Upper Bound
Thin
doll group
Realistic doll group
3.600*
.168
.000
3.20
4.00
Control group
3.567
.168
.000
3.17
3.97
Realistic doll group
Thin doll group
-3.600*
.168
.000
-4.00
-3.20
Control group
-.033
.168
.979
-.43
.37
Control group
Thin doll group
-3.567*
.168
.000
-3.97
-3.17
Realistic doll group
.033
.168
.979
-.37
.43
*. The mean difference is significant at the 0.05 level.
Descriptives
BPDS
N
Mean
Std. Deviation
Std. Error
Thin doll group
30
5.07
.868
.159
Realistic doll group
30
1.47
.507
.093
Control group
30
1.50
.509
.093
Total
90
2.68
1.816
.191
Your Turn: Evaluating Output
Alex Brylov/Shutterstock
Based on the results of your statistical analyses, provide the values in the “Answer” column that correspond to the terms in the “Prompt” column.
F for the ANOVA test
F for the ANOVA test
df for the main effect of group (between-groups)
df for the main effect of group (between-groups)
df for error (within-groups)
df for error (within-groups)
p for the ANOVA test
p for the ANOVA test
p for the difference between thin doll and realistic doll groups
p for the difference between thin doll and realistic doll groups
p for the difference between thin doll and control (no doll) groups
p for the difference between thin doll and control (no doll) groups
p for the difference between realistic doll and control (no doll) groups
p for the difference between realistic doll and control (no doll) groups
eta2eta2
Question
zRTKvrv4duxOfReKGdT+SZETc+NumvPhPT1TTf+fXI/xjEK6
Activity: Graphing Results
chapter_9_graph_activity
In order to visualize your data, use the values on the previous screens to input the mean that corresponds to each group listed in the output. Then, check out the graphic representation of your data, below.
Descriptives
BPDS
N
Mean
Std. Deviation
Std. Error
Thin doll group
30
.868
.159
Realistic doll group
30
.507
.093
Control group
30
.509
.093
Total
90
2.68
1.816
.191
Dolls & Body Dissatisfaction
Mean BPDS Score
Doll Group
Question
6kGi4efK+HrmwDLrQ+gwgavTfcRTAUg4Sof/F0kWwoMRG03T
Your Turn: Results
gguy/Shutterstock
Now that you have worked with your data, you must determine the best way to express your findings in written form. You must be sure that how you describe your findings accurately represents the data.
Now that you have worked with your data, you must determine the best way to express your findings in written form. You must be sure that how you describe your findings accurately represents the data.