Research 2 – Research in Psychology 2

1st Semester, AY 2021 - 2022

Module 2 (Data Analysis)

I. Topics

A. Data Collection

1. Data Analysis
2. Common Indicators in Research
3. Method of Choosing Data Analysis
4. Performing Data Analysis
5. Interpretation of the Data Analyzed

II. Learning Objectives

At the end of the chapter, the students should be able to:

A. What is data analysis?
B. What are the common indicators used in educational research?
C. How is the method of data analysis determined?
D. How are some of the computations actually performed?
E. How are the results of the study interpreted?

III. Content

A. Data Analysis

Data Analysis is one of the most vital parts of a research. It is a process of making sense of your
data, usually through the statistical analysis of participants’ scores in questionnaires or an analysis
of the participants’ interview. Through this process, the true essence of research is established.

One’s analysis of data is highly reliant on the study’s research design. Various analytical tools are
utilized whether the paper is quantitative or qualitative. For example, Pearson correlation is used
for quantitative correlational designs, while interpretative phenomenological analysis (IPA) is
used for qualitative phenomenological studies.

For quantitative studies, aside from knowing the study’s research design, it is important to identify
if the data is parametric or non-parametric. Data are considered as parametric if they are
interval/ratio or if they are normally distributed. Meanwhile, non-parametric data are nominal or
ordinal in nature, and they are not normally distributed. Statistical analysis to be applied to the data
gathered by the researcher(s) vary depending on the aforementioned factors.

For qualitative studies, similar to quantitative studies, it is important to take the research design
and the participants into consideration. Qualitative studies often have philosophical underpinnings,
hence, it is important that researchers are also well-versed with philosophical movements that
inspired the various methods of analyzing qualitative data.

B. Common Indicators in Research

Indicators in research measure how well you are making progress. This can be in the form of how
many participants you have collected data from, how much you have written in your paper, how
many references you have reviewed, and so much more.

In data analysis, however, there are also indicators that dictate how you should analyze your data.
In the previous section, it was briefly mentioned that whether the data are parametric or non-
parametric is one of the indicators you should consider when deciding how to proceed with your
data analysis. In this section, you will know more about what indicators to consider when analyzing
your data.

1. Research Design – Quantitative data are analyzed using statistical tools. Meanwhile, qualitative
data are analyzed using particular approaches that have philosophical underpinnings.
QUANTITATIVE QUANTITATIVE DATA QUANTITATIVE
RESEARCH DESIGN ANALYSIS DATA ANALYSIS
MEANING
Descriptive Descriptive Statistics Statistical tool to
describe the data in
terms of their mean and
standard deviation
Correlational Correlational Statistics Statistical tool to
determine if two or
more variables have
relationships.
Predictive Regression Analysis Statistical tool to
determine if one
variable influence
another
Comparative t-test or ANOVA Statistical tool to
compare the difference
between two or more
groups
QUALITATIVE RESEARCH QUALITATIVE DATA QUALITATIVE
DESIGN ANALYSIS DATA ANALYSIS
MEANING
(flexible) Thematic Analysis Analyzing participants’
interview by clustering
their statements into
major themes
Phenomenology, Case Study, Interpretative Phenomenological Analyzing how the
Ethnographic Studies Analysis (IPA) participants’ make
Heideggerian Phenomenology sense of their life world
 in the context of their
own interpretation
Phenomenology, Case Study Descriptive Phenomenological Analyzing participants’
Analysis (DPA) life world without
Husserlian Phenomenology taking into
consideration their
interpretation
Ground Theory Grounded Theory Analysis Analyzing interviews
until researchers arrive
to core themes and core
theories

2. Number of Participants – Both in quantitative and qualitative research designs, the number of
participants must be considered before proceeding to data analysis. For example, in testing the
normality of data in a quantitative analysis, a sample size of less than 50 must be analyzed for
normality using Shapiro-Wilk, while a sample size of more than 50 must be analyzed for normality
using Kolmogorov-Smirnov. In qualitative studies, IPA and DPA often requires at least 8-10
participants. In ground theory, 40 participants are recommended to be interviewed.

3. Levels of Measurement – Most of what we encounter in quantitative data analysis involves an

analysis between interval/ratio variables. (eg. Depression level and anxiety level). Using the
aforementioned example, say, we would like to know the relationship between the two, we may
consider Pearson correlation assuming that the data is parametric. However, if we would want to
test the relationship between sex (categoric variable) and depression level (interval/ratio), we may
want to use eta correlation instead of Pearson correlation.

4. Normality of Data – A skilled researchers knows when to utilize parametric and non-parametric
tests, depending on the normality of data. (See table below to determine what appropriate test to
use)

C. Method of Choosing Data Analysis

The first question to answer in order to choose the appropriate data analysis strategy is determining
whether your study is quantitative study.

For quantitative studies, the following steps may be considered to arrive at the most appropriate
data analysis tool:

1) Determine what quantitative research design you are utilizing in your study (eg. Descriptive,
Correlational, Causational, Comparative).
2). Determine if your data is parametric or non-parametric, and also consider if your data is
interval/ratio or categorical.
3) Determine the number of participants or groups you’re including in your analysis.
Below is a table of tests that you can refer to depending on the research design and the number of
participants in your research.
Parametric Non-parametric Categoric
1 Group One Sample T-Test Binomial Chi-Square
2 Independent Groups Independent T-Test Mann-U-Whitney Chi-Square
2 Dependent Groups Paired T-Test Wilcoxon McNemar Test
>2 Independent Groups One-Way ANOVA Kruskal Wallis Chi-Square
>2 Dependent Groups Repeated ANOVA Friedman Cochran Q
Ratio (Correlation) Pearson Correlation Spearman-Rho Eta (parametric or
non-parametric
and categoric
Chi-Square
(categoric and
categoric)
Model (Regression) Simple Linear Multiple Linear Logistic
Regression Regression Regression
Experimental Design Two-Way ANOVA ANCOVA MANOVA

For qualitative research, the following steps may be considered to arrive at the most appropriate
data analysis approach
1) Determine your research designs.
2) Determine your research objective
 If you simply want to cluster the participants’ statements into themes, use thematic
analysis.
 If you want to know the lived experiences of participants considering their interpretations
and the context of their experiences, use IPA.
 If you want to know the lived experiences of participants and only aim to describe their
objective experiences, use DPA.
 If you want to create a new theory, use Grounded Theory.

D. Performing Data Analysis

For quantitative studies, data is often analyzed with the help of statistical softwares. The most
common softwares used by students and professionals in psychology are Statistical Package for
Social Sciences (SPSS), STATA, and GNU PSPP. Usually, statistical software does all the work
and generate all the output needed by the researchers.

For qualitative studies, while most data are coded and analyzed in Microsoft excel, the so-called
“word miners” such “NVIVO” is used to help the researchers search for the most commonly
appearing statements of participants.

Qualitative data, no matter what research design or data analysis is utilized, often undergoes the
process of coding. Coding begins wherein 1) the significant statement from the participants’
interview response is summarized or reduced to a “chunk statement.” 2) After reducing all
statements into chunks, the participants’ summarized statements are grouped into subcategories.
3) Finally, these subcategories are reduced to major themes. Qualitative studies have a limit of
coming up to seven themes.

E. Interpretation of Analyzed Data

Interpreting the data analyzed from either quantitative or qualitative studies can be written in
different ways. However, for both research designs, there are general rules in how to interpret and
report your analyzed results or findings.

In quantitative studies, it is important that the questionnaire you used to gather data has a readily
available interpretation for scores, otherwise, you’ll have to conduct norming. For example, if a
participant obtained a score of 10 in conscientiousness, the questionnaire must be able to tell if
that score falls within low, moderate, or high range.

Descriptive data analysis must be interpreted by citing the mean scores and the standard deviation
of the scores you analyzed. Both the mean scores and standard deviation are readily available from
the output generated by statistical software. Meanwhile, in inferential data analysis such as
correlation, regression, t-test, and ANOVA, the significance level and certain coefficients are
reported. For example, in Pearson correlation, the p-value or the significance level and the
correlation coefficient (represented by the letter ‘r’) are included in the report.

Interpretation of qualitative data analysis, on the other hand, is more complex and time-consuming
compared to quantitative data analysis.

The first step in qualitative data analysis is the use of bracketing. It is the process of writing our
biases and being aware of them in order to avoid injecting our own assumptions in interpreting the
participants’ statements. It is called bracketing, since in doing the process, we literally put a bracket
in our written biases and separates them from the participants’ significant statements.

After bracketing, we follow particular guidelines in interpreting our analyzed data. Each analytical
approach in qualitative data we use have particular steps. For example, in IPA, we follow the three-
step cycle recommended by Alase (2017). In thematic analysis, we follow the six steps
recommended by Braun and Clarke (2013).

Finally, in qualitative studies, we use triangulation. It is a process of validating our interpretation

in our gathered data. Triangulation can be accomplished through four methods. The first one is
through data triangulation, in which we use multiple data sources to understand a phenomenon.
This also involves confirming your interpretation to the participants you interviewed. The next one
is method triangulation, in which multiple methods are utilized to understand a phenomenon.
The third one is theory triangulation in which we use multiple perspectives to interpret and
explain data. Finally, we use investigator triangulation in which multiple researchers cooperate
in collecting and interpreting data. This also involves hiring an external validator who is not a co-
author of the study in order to cross-check the researchers’ interpretation of the qualitative data.
Guide Questions

A. What is data analysis?

B. What are the common indicators used in educational research?
C. How is the method of data analysis determined?
D. How are some of the computations actually performed?
E. How are the results of the study interpreted?

IV. Self-Test

1. What are the key points in the module?

______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________

2. Based on your readings, how can you apply the content from this module to your daily life?
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________

3. What insights did the module provide in your course?

______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________

4. How has class discussion influenced your thinking on this module?

______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
5. How can the learnings in this module improve your role in your school, family, and community?
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________
______________________________________________________________________________

V. Post Test
A. Choosing Your Data Analysis

With your groupmates, answer the following question to help you determine what data analysis
tool or approach you will use for your research paper:

1. What is your research design?

a. Specifically identify what particular quantitative or qualitative research designs you are
utilizing.
2a. For quantitative studies:
2a1. Is your data parametric, non-parametric, or categoric?
2a2. What are the levels of your data’s measurement?
2a3. How many participants/groups are involved in your study?
2b. For qualitative studies:
2b1. What are your research questions?
2b2. Describe the characteristic of your participants. (Are they minorities? Are they a part
of a cultural group? What’s their age? Sex? Gender? Etc.)
2b3. How many participants/groups are involved in your study?
3. Write a short paragraph justifying your choice of data analysis tool or approach.
 Rubrics
Excellent Very Good Satisfactory Need for Poor
Improvement
Quality of 21-25 16-20 11-15 6-10 1-5
Output The output The output The output The output Basic
submitted is submitted is meets the submitted research skills
well-written written in quality barely the are not
and is of scientific and standards of quality evident in the
high-quality. scholarly tone, a scientific standards of a submitted
Scientific however, a paper, though scientific output.
and scholarly few details in improvement paper. Many Student may
tone are the written is evidently details are want to have
evident with output are needed to omitted, and refresher
the written missing. enhance the there is a lack courses on
output. scholarly of scholarly research
nature of the nature in the writing.
output. output.
Dutifulness 9-10 7-8 5-6 3-4 1-2
and Necessary Requirements Necessary Requirements Little to no
Punctuality requirements were passed a requirements are passed requirement
are often bit late and were passed significantly were
passed earlier most of the later than the later than the submitted or
or on time. necessary assigned assigned time, no tasks were
The student tasks were time, and and numerous accomplished.
has accomplished. several tasks things are
accomplished were not missing for
all the accomplished the assigned
assigned requirements.
tasks
dutifully.
Research 13-15 10-12 7-9 4-6 1-3
Mastery Student Student is Standard The student Little to no
display mostly quality of lacks the mastery is
excellent knowledgeable research is necessary evident with
mastery in about the manifested knowledge the student.
both the technical by the and skills The student is
technical aspects of student, and both in also evidently
aspects of research and the student research unaware of
research and their research display writing and in their paper.
in their paper per se. sufficient their paper per
research knowledge of se.
paper per se. their own
paper.