PSY 3213 Research Methods in Psychology

Gratitude Experiment Paper Guide

Michiko O. Clutter, PhD
The Goal ———————————————–
Writing Hypothesis ———————————-
Writing Method ————————————–
Conducting Data Analysis————————–
Reporting Stats using APA Format ————–
Preparing Table and Figure ———————–
Writing Results ————————————–
Writing Introduction ——————————-
Writing Discussion ———————————-
Submitting Your Paper —————————-
Paper Grading Criteria —————————- 2
3
4
9
10
13
14
15
16
17
18
The goal of this paper assignment

The goal of the paper assignment is to learn and demonstrate the following basic skills in conducting research in psychology.

– Writing a lab report using APA style
– Analyzing and interpreting experimental data using SPSS
– Conducting literature review using computerized database (PsycINFO)
– Organize statistics and present them graphically as Figures and Tables
– Introducing and discussing the findings from this study and other relevant studies concisely and accurately

An additional benefit of this paper assignment is that you will learn different methods of boosting happiness through literature review.

In essence, this paper will integrate all the skills you acquired in Research Methods in Psychology!

You will be asked to demonstrate the above skills based on a secondary data analysis of a previously completed experiment. This is an experiment that aims at
improving psychological well-being (PWB, a.k.a. happiness) through enhancing the sense of gratitude (Gratitude Experiment In-Class Demonstration PowerPoint slides).

The format of your final paper should closely follow the APA format. You must have all of the following sections: Title page, abstract, introduction, method, results,
discussion, references, tables and figures (figure caption)

You are strongly encouraged to turn in the drafts of Hypotheses, Method, Results, Introduction and Discussion sections (in this order) to your instructor by the due
dates posted on Syllabus. For other types of help (e.g., grammar, style), you may also use Writing Center (Terrace 301). But be sure to check your paper for APA style
formatting yourself.

Feel free to download APA Style Template and use it for your paper.

For general guidelines as to how to organize each section of the paper, please consult General Guideline – Writing an Empirical Paper in APA Style.

Don’t forget to consult the grading rubric for this paper as you work through different sections of your paper (see page 16)

Feel free to ask the instructor or TA if you have any questions.
Good luck, and enjoy your happiness boosting journey

Writing Hypotheses

As we already know, hypotheses are the testable statements of our predictions of the results based on what we know (i.e., previous literature review), and it is
included at the very end of the Introduction. Because this is an experiment, we predict how the DVs (psychological well-being (PWB) variables, i.e., positive affect,
negative affect, and satisfaction with life) will respond to the manipulation of IV (gratitude exercise). We also explore whether this experimental manipulation has
different effect on PWB based on the levels of social support at the baseline.

Be sure to include two hypotheses, one for the main effect of the experimental manipulation and the other for the moderator effect of social support on the effect of
experimental manipulation. Here are sample hypotheses:

The first hypothesis in this study tested the overall efficacy of the gratitude exercises. It was hypothesized that, relative to the control task, practicing gratitude
would lead to improved psychological well-being (as measured by increased positive affect and life satisfaction, and reduction in negative affect) after the
intervention.
The second hypothesis concerned with whether the levels of social support moderate the effects of gratitude exercises on psychological well-being. We predicted that
students who reported lower levels of social support would report greater gains in psychological well-being relative to students who reported higher levels of social
support prior to the intervention.

You see how it first states what it is (the big picture) that we’re interested in testing, followed by the specific predictions of how you think the DVs will respond
to the manipulation of IV.

Now go ahead and write your own.

Writing Method Section

Your methods section consists of the following components: Participants, Design, Procedures, and Materials. Here’s an outline of the information that needs to go into
each sub-section.

Participants (don’t use the word “Subject”)
o Undergraduate students enrolled at a University in a Western state; All students participated for course credit (Introductory Psychology)
o Get the following information from your dataset
o # of students enrolled into the study
o # of students in the final analytic sample (how many had missing data and not included in the analyses?)
o Describe demographic variables: ethnicity (% for each category), age (range, M, SD) and gender (% female)

Design
o 2 (Activity: Gratitude vs. Control) x 2 (Social Support: Low vs. High) factorial design
o Participants were randomly assigned to either Treatment (n=?) or Control (n=?) Groups

Procedure
1. Introductory appointment in the lab
o This is an Internet-based study (used a Web site only accessible to participants)
o You met a “batch” of participants (groups of 5-10 at a time).
o You provided instruction as follows:
2. Baseline assessment
• You told the students to access the study website on their own after the lab visit to answer a series of questionnaires, including the consent form,
demographic questions, and the baseline measures on PWB and other relevant variables (see Materials for the description of each variable)
3. Experimental Manipulation (Intervention)

 You created the website so that the students are automatically randomized to one of two conditions (T or C) for an 8-week period. The website gave the
following instructions for each group:

 Gratitude Intervention Group: You told the students to spend 15 min per week for 8 weeks to remember times in their lives when they were grateful for something
that another person did for them and then writing about those experiences, as follows:

Here’s an example of one week’s gratitude letter provided by one of your participants:
Dear Mom and Dad,
Thanks for supporting me for the past 3 years. You guys are my strength and hope. You were the ones who pushed me and directed me. Without you two I would be lost.
Thanks for always having hope in me and knowing what I can do and telling me when I’m going the wrong way. Thanks for giving me confidence for things that I thought I
could never accomplish. You guys are the greatest parents one could ever hope for. Dad, you have helped me a lot through my college career – pushing me to talk to my
advisor and other faculty members when I don’t have the guts to. Mom, thank you for cheering me up when I’m feeling depressed because I’m struggling with a class. I
feel like I could tell you guys anything, which I usually do. I hope to someday give back to you guys everything that you have given me. Whatever I do in the future, I
will keep what you guys have taught me in mind. I will not let you guys down!
• Control Group: You instructed the students to 15 min per week over 8 weeks listing what they did over the past 7 days. To maintain the cover story that all
participants (including control group participants) were expected to increase their happiness levels, you described this control condition as a task that will hone the
students’ organizational skills.
Below is an example of what one student wrote during one particular week of this condition:

1.) Went golfing at a local golf course with my brothers and father. 2.) Watched the NFC and AFC championship this weekend on television with my family. 3.) Played
Tiger Woods PGA Tour 2006 for a few hours this weekend. 4.) Studied for biology quiz and exam coming up in the next couple of weeks. 5.) Studied for Psychology 1 Quiz
and exam in the coming week. 6.) Completed homework for statistics. 7.) Read 6 Chapters of biology textbook over the weekend that took about 10 hours. 8.) Talked with
a high school friend on AOL Instant Messenger for a couple of hours last week. 9.) Worked on accounting homework for several hours on the weekend. 10.) Went out to
dinner with family on the weekend. 11.) Helped out my dad by cleaning the whole house and doing yard work. 12.) Went to my dad’s business to work for a few hours. 13.)
Woke up and went to school everyday for most of the day (7 am until about 4-5 pm) 14.) Read the Bible at night before bed. 15.) Read a motivational book. 16.) Play
with my cats each day and take care of them. (been taking care of them for 8 years)

4. Follow-up Assessment

• You programmed the website so that after the 8-week intervention period, the students completed the measures of PWB (the ones that you administered at the
baseline).

Materials

• Please identify previous research articles describing the use of these measures to learn how to display information for each measure: e.g., name of scale,
author, # of items, representative items, scale format, reliability & validity from previous study, reliability from current study, how the scores were calculated and
used)
• You can find the original published studies that reported the development of the scale under Paper Assignment  Background Literature folder

• The Gratitude Questionnaire-6 (GQ-6):
• The alpha coefficients were .87 (baseline) and .84 (follow-up) in this study

• Positive Affect and Negative Affect Schedule (PANAS; Watson, Clark, & Tellegen, 1988): See the original article for description of this measure
• Let’s pretend that alpha coefficients in our study were as follows:
• Positive affect at Baseline: .87
• Positive affect at follow-up: .82
• Negative affect at baseline: .84
• Negative affect at follow-up: .89

• Satisfaction With Life Scale (SWLS; Diener, Emmons, Larsen, & Griffin, 1985)
• Alpha coefficients at the baseline and follow-up assessments were: .92 (baseline) and .86 (follow-up)

• Interpersonal Support Evaluation List (ISEL): To measures social support (only at the baseline assessment), you used this scale. The scale information is found
in “Interpersonal Support Evaluation List.doc”.
• The alpha coefficients at the baseline and follow-up assessments were .72 (baseline). You dichotomized the scores using the median split to categorize students
into high vs. low social support.

Conducting Data Analysis

Your dataset is “Gratitude Experiment Data.sav”

1. What is the IV? Subject variable? Dependent variables? How are they coded in the dataset?
2. Find out the total sample size? Is there any missing data?
3. Find out n in each randomized group. Is the rate of missing data different between randomized groups (Gratitude vs. Control)?
4. Summarize demographic variables for the overall participants (age, gender, ethnicity)
5. Check for the distribution of study variables at the baseline and follow-up assessments (are they roughly normally distributed? Within the expected range of
scores?)
6. Compute change scores – For PA, SWL, and GRAT, use T2-T1 (to show increase in values); for NA, use T1-T2 (to show decrease in values)
7. Get descriptive statistics (M, SD, min, max) for: Baseline, Follow-up, and change scores. Make sure that there is no problem with the dataset (e.g., data mis-
entry).
8. Test to see if randomization worked.
a. Make sure that the dependent variables measured at the baseline assessment don’t differ between groups
b. Make sure that the demographic variables measured at the baseline (age and gender) don’t differ between groups
9. Do a manipulation check. Make sure that the change score in gratitude is greater for gratitude group than for control group.
10. Test your first hypothesis (main effects of the gratitude intervention).
a. Remember your first hypothesis was: “relative to the control task, practicing gratitude would lead to improved PWB (as measured by increased positive affect
and life satisfaction, and reduction in negative affect) after the intervention”
11. Test your second hypothesis (2×2 factorial design – does the intervention effect differ by baseline levels of social support?)
a. Your second hypothesis was: “students who reported lower levels of social support at the baseline would report greater gains in PWB relative to students who
reported higher levels of social support”
12. Create tables & figures
a. Table 1. Effects of experimental conditions on the changes in PWB
b. Create Figure(s) for interaction effect(s) (if any)

Reporting Results of Statistical Analysis Using APA Format

• When you write up the Results section, focus on reporting the results of the data analyses using the APA format. You should include minimal (if any)
interpretation of what the result means/implies in the larger context of the study. The interpretation of your results should be saved for Discussion.

• Do not discuss any methodological procedures or whether your results support or did not support your hypothesis. Focus on (a) preliminary analysis (e.g.,
testing to see if the groups are equivalent at the baseline; randomization check) and (b) testing the hypotheses stated in Intro.

• Every statistical test that you report should relate directly to a hypothesis. Begin the results section by restating hypothesis, then state whether your
results supported it, then give the data and statistics that allowed you to draw this conclusion.

• When you have multiple numerical results, use a Table or a Figure to summarize the information more effectively.

• When you report the results of statistical analyses, typically follow the following format: State what is going on in English, report descriptive statistics
along with it (M, SD for quantitative variables, n, % for qualitative variables), followed by test statistic, degrees of freedom, obtained value of the test, p value,
and effect size.

• Test statistics and effect size should be rounded to two decimal places. % values are often rounded to the first decimal (e.g., 32.0%).

• All statistical symbols (M, SD, t, p, n.s., r, N, n, etc.) must be italicized.

• When reporting a significant difference between two conditions, indicate the direction of this difference, i.e. which condition was more/less/higher/lower than
the other condition(s).

• Decimal Fractions – Rule of thumb: Round to two decimal places
• For numbers less than 1
• If statistic can exceed 1  use 0 before decimals (e.g., 0.23 cm, 0.48 s, t (30) = 0.43, M = 0.98, SD = 0.43)
• If statistics can only be less than 1 Don’t use 0 before a decimal r = .43

• Reporting P values in text – Report exact p values to 2 or 3 decimal places (new)
p = .31
p = .031
p = .003
Report p values less than .001 as p <.001 (same as before)
Examples

Reporting a significant dependent samples t-test (μ1 ≠ μ2):

Results indicate a significant preference for pecan pie (M = 3.45, SD = 1.11) over cherry pie (M = 3.00, SD = .80), t (15) = 4.00, p = .003, r = .23.

Reporting a significant independent samples t-test (μ1 ≠ μ2):

UW students taking statistics courses in Psychology had higher IQ scores (M = 121.00, SD = 14.20) than did those taking statistics courses in Statistics (M = 117.00,
SD = 10.30), t (44) = 3.23, p = .025, r = .44.

Over a two-day period, participants drank significantly fewer drinks in the experimental group (M = .67, SD =
1.15) than did those in the wait-list control group (M = 8.00, SD = 2.00), t (4) = -5.51, p = .013, r = .92.

Reporting a significant omnibus F test for a one-way ANOVA:

An analysis of variance showed that the effect of noise was significant, F (3,27) = 5.94, p = .041, η2 = .18 . Post hoc analyses using the Scheffé post hoc
criterion for significance indicated that the average number of errors was significantly lower in the white noise condition (M = 12.4, SD = 2.26) than in the other two
noise conditions (traffic and industrial) combined (M = 13.62, SD = 5.56), F (3, 27) = 7.77, p = .032, η2 = .22.

Reporting results of major tests in factorial ANOVA; non-significant interaction:

Attitude change scores were subjected to a two-way analysis of variance having two levels of message discrepancy (small, large) and two levels of source expertise
(high, low). All effects were statistically significant at the .05 significance level. The main effect of message discrepancy yielded an F ratio of F (1, 24) = 44.40,
p < .001, η2 = .65 indicating that the mean change score was significantly greater for large-discrepancy messages (M = 4.78, SD = 1.99) than for small discrepancy
messages (M = 2.17, SD = 1.25). The main effect of source expertise yielded an F ratio of F (1, 24) = 25.4, p = .004, η2 = .51 indicating that the mean change score
was significantly higher in the high-expertise message source (M = 5.49, SD = 2.25) than in the low-expertise message source (M = 0.88, SD = 1.21). The interaction
effect was non-significant, F (1, 24) = 1.22, p=.34, η2 = .05.

Reporting results of major tests in factorial ANOVA; significant interaction:

A two-way analysis of variance yielded a main effect for the diner’s gender, F (1,108) = 3.93, p = .045, η2 = .04, such that the average tip was significantly higher
for men (M = 15.30%, SD = 4.44) than for women (M = 12.60%, SD = 6.18). The main effect of touch was not statistically significant, F (1, 108) = 2.24, n.s., η2=.02.
However, the interaction effect was significant, F (1, 108) = 5.55, p = .032, η2=.05, indicating that the gender effect was greater in the touch condition than in the
non-touch condition.

Reporting the results of a chi-square test of independence:

A chi-square test of independence was performed to examine the relation between religion and college interest.
The relation between these variables was significant, χ2 (1, N=88) = 14.14, p =.008, φ=.32. Catholic teens (35.0%) were less likely to show an interest in attending
college than were Protestant teens (48.0%).

Making Table & Figure

How to make Tables

• It’s often helpful to wait to make a table until you completed all the analyses that you need for the entire paper.
• DO NOT use Tabs – Tabs are for the dinosaurs; we must use the Table function in MS Word
• On a piece of paper, write out what information goes in which columns and rows. This will help you determine the number of rows and columns you need in your
table from the get-go
• All Tables must be double-spaced
• For our study (specifically, for the tests of Hypothesis 1), please make a table that looks similar to Table 4 on the Emmons & McCullough (2003) article. This
will be your Table 1 (Effects of experimental conditions on the changes in PWB)
List all 4 variables
Gratitude
Positive affect
Negative affect
Satisfaction with life

How to make Figures

• Figures are typically used when you want to visually display complex results, such as a statistically significant interaction effect
• Create Figure(s) for interaction effect(s) if any of them are statistically significant (if not statistically significant, then there is no point in creating a
Figure for it)
• Open Figure Template Excel file
• When you complete the relevant analyses in SPSS, copy and paste the mean scores onto the template for the different cells (typically found at the beginning of
the factorial ANOVA output)
• Once you finished making the figures in Excel, copy and paste onto your main paper (in Word).
• Figures generated by SPSS must NOT be copied and pasted onto the paper.

Writing Results Section

Your results section should consist of the following components: Preliminary analyses, manipulation check, and tests of hypotheses.

Here’s a basic outline of the information that you should include in the sub-sections of the results section. Remember, whenever you make a statement about your data
in results section, you must back it up with the results of your analyses

Preliminary analyses
• Explain how change scores were computed (follow-up score minus baseline score for PA, SWL, and gratitude; for baseline score minus follow-up score for NA).
These change scores were your dependent variables.
• Explain the rationale for using change scores – represents the amount of changes that occur over the course of the study relative to the participant’s own
baseline value.
• How you (supposedly) computed the dichotomous social support score – you computed the total score for social support scale and used median-split to categorize
people into high and low social support ***the values are already provided in the dataset
• Are the two randomized groups (Gratitude vs. Control) equivalent with respect to demographic characteristics and DVs? Look at age and gender.

Here are some sample write-ups:
At the baseline assessment, there was no difference in the positive affect scores between gratitude (M=3.04, SD=0.65) and control (M=3.12, SD=0.71) groups, t
(138)=0.70, p=.488, r=.06.

There was no statistically significant difference in the distribution of participants’ gender between the gratitude (70.0% female) and the control groups (65.7%
female),
χ2(1, N=140)=0.30, p=.587, φ=.05.

Manipulation check
• Show whether manipulation worked by comparing the gratitude change scores between the two groups

Test of hypothesis 1
• Paraphrase your first hypothesis to remind readers what it is
• Explain what statistics you used (independent samples t-tests) for which DVs to test this
• Summarize the results, while referring to Table 1

Test the hypothesis 2
• Paraphrase your 2nd hypothesis to remind readers what it is
• Explain what statistics you used (2×2 factorial ANOVA) – be sure to specify levels in each IV
• Summarize the results, while referring to Figure 1

Writing Introduction

General Requirements

 Always begin with a detailed outline – know what to say in each paragraph before you start writing!
 Cite authors; paraphrase what they say about the point you want to make (do not plagiarize); don’t quote unless you are quoting a Greek philosopher, etc.
 In addition to the key reference articles provided for the background literature, cite at least 5 additional studies/articles for the entire paper (to talk
about their studies, compare your results against others, etc.) – use PsycINFO
 Don’t forget to include all of your cited studies in References section.

Specific guideline for this assignment:

• Give background. This section gives the history behind your research question. Identify the key research done in the area so far and the value of your study.
• Why is happiness an important topic to study? Why care about increasing happiness? Convince the reader citing previous work in psychology, philosophy, history,
etc.
• How did other researchers increase happiness? (talk about different strategies used)

• Cite all relevant research, not just the studies whose results you agree with. Identify studies that support contradictory findings, and suggest what might
underlie the differences (look especially at the introduction and discussion sections of the articles you are comparing)
• Now, cite relevant studies that used similar technique as yours (i.e., gratitude intervention)

• What is the remaining area of research that we don’t know about? – remember, we are looking to see if people with lower social support benefit more from the
intervention? Is this novel? Look into the literature and find out!
• You might want to look into the correlational research examining the relationship between social support and happiness (SWB)

• State hypotheses and predictions. At the end of the introduction, state the hypothesis that you tested and specific predictions that follow from it
• What is PWB – operational definition of happiness, right? Before you start using the terms like this, be sure to tell the readers what they are.

Writing Discussion

• First, remind the readers what your research questions were

• For each hypothesis, discuss whether the results supported it or not
a. If not, speculate why it did NOT support your hypothesis
b. You could also state that the your findings partially supported your hypotheses, and talk about each result (for each DV)

• Are your results consistent with prior studies that you described in Introduction? Talk about your converging and diverging results and discuss why they do or
do not converge (different populations? Different methods/designs/measures? Any other things that could have contributed to your diverging results?)
a. Be sure to use reasoning that are not “far-fetched”

• Limitation of the research & future research directions – anything else that could have affected your internal validity of the study? Any other confounding
variables that you wish you’d control for? State how others doing this type of research in the future could improve their studies
a. Avoid overstating the importance of your findings. Be modest
b. Don’t over-generalize – you did not solve the entire humanity’s problem. Don’t draw conclusions that are beyond what our data can speak of
c. Stay focused on the research question. Don’t digress

• Conclusion
a. Although you should acknowledge problems or weaknesses of your design, end the paper on a high note.
b. Summarize the study’s strengths, conclusions, implications and/or ideas for future research.
Title Page, Abstract, and References

See General Guideline – Writing an Empirical Paper in APA Style
Submitting Your Paper

Congratulations! You’re almost done with this paper assignment! Be sure to assemble everything in this order.

 Grading criteria (on page 18)
 Title Page (this is your first page)
 Abstract
 Introduction
 Method
 Results
 Discussion
 References
 Table
 Figure (this should be your last page of your paper)

The key is to put everything into a single Word Document – from Title page through the Figure.

Don’t forget to print the grading criteria (see next page) and attach it on top of your paper.

Staple everything, and submit the hard copy (don’t forget to staple everything) AND electronic copy on or before the due date.

NO LATE PAPERS WILL BE ACCEPTED. If you MUST turn in your paper late, 10 points will be deducted for every day that this paper is late.

Student’s Name: ______________________________________
Gratitude Experiment Paper
Submit hard copy and electronic copy (through Blackboard)

(10 points) Title Page & Abstract
(2) Title page
(2) Problem/hypothesis explained
(2) Methods
(2) Results
(2) Conclusions

(20 points) Introduction
(12) Background/literature search (what has been done so far?)
(4) Hypothesis development (What is/are your hypotheses?)
(4) Completeness and style

(20 points) Methods
(4) Participants (Who were your participants?)
(4) Measures/Materials (operationalization of variables)
(4) Design (correlational, experimental, etc.? If correlational, what are the
variables to examined? If experimental, what is the IV and DV?)
(4) Procedure (What did participants do? How were variables/measures
administered?)
(4) Completeness and style

(16 points) Results
(4) Discussion of analysis (what statistical test(s) was/were used?
What did you find?)
(4) What variables are being related/compared?
(2) Direction of results (pos or neg correlation? Which group is higher?)
(6) Tables/figures/graphs

(16 points) Discussion
(2) Hypothesis, supported or not?
(4) Interpretation of results, discussion of confounds
(4) Theoretical impact/limitations
(4) Future potential studies

(6 points) References (Reference page? At least 5 additional references on top of required
references?)
(6 points) APA Style (Follow APA style throughout?)
(6 points) Proofreading (Any typing errors? Paper carefully edited?)

(100 points) TOTAL SCORE
10 points will be deducted for every day that this paper is late.
TO HAVE YOUR ASSIGNMENTS DONE AT A CHEAPER PRICE, PLACE THIS ORDER OR A SIMILAR ORDER WITH US NOW.