Analyzing the Meaning of the Data and Drawing Conclusions

Correct data leads to correct presentation of results and discussion.

For a researcher to avoid delays regarding data interpretation and analysis, he shall know the
differences and criteria needed for certain data analyses.

On Writing Results and Discussion

Results and Discussion is the chapter that presents all the data gathered and analyzed. In this
chapter, researchers are expected to present the data per problem to ensure organization.

On Writing Results and Discussion

Without this chapter, the questions presented in the Statement of the Problem will not be
answered. With that, remember to present your data the way how you presented your research
questions.

On Presenting Data
As mentioned in the previous slides, it is important for a researcher to go back to the SOP.
It needs to be done to ensure proper organization.

On Presenting Data
Before contextualizing the contents of the chapter based on the chosen research approach,
researchers could present their data through the following:

Textual Presentation
Graphical Presentation
Tabular Presentation

On Presenting Data
A researcher can use some of the ways or even combine them all. However, there are instances
where graphical and textual presentation are used to show data effectively.

On Comparing Data
After presenting the data, you need to compare your data from other sources to establish the
similarity or difference of them. It is important for us to do this because:
● We need to make sure that our data can be related to another research
● We need to form connections among the body of knowledge available.
On Comparing Data
Generally, qualitative and quantitative data presentation and comparison share same structure.
A more contextualized example for qualitative data presentation will be presented later.

Qualitative Data Analysis

– Thematic Analysis Analyzing the Meaning of the Data and Drawing Conclusions

Thematic Analysis
It is a method of analyzing qualitative data. It is usually applied to a set of texts, such as an
interview or transcripts. The researcher closely examines the data to identify common themes –
topics, ideas and patterns of meaning that come up repeatedly.

When to Use Thematic Analysis

Researchers tend to use thematic analysis when their research questions wanted to answer
problems through exploration of one’s idea or experience.

When to Use Thematic Analysis

Some examples of those questions are:

How do patients perceive doctors in a hospital setting?
What are young women’s experiences on dating sites?
What are non-experts’ ideas and opinions about climate change?
How is gender constructed in high school history teaching?

Thematic Analysis
Thematic analysis is often quite subjective and relies on the researcher’s judgement, so you
must reflect carefully on your own choices and interpretations.
Six Steps in Conducting Thematic Analysis by Braun and Clarke (2013)
Steps in Conducting Thematic Analysis

Step 1: Familiarization
Step 2: Coding
Step 3: Generating themes
Step 4: Reviewing themes
Step 5: Defining and naming themes
Step 6: Writing up

Step 1. Familiarization
Get to know your data.

Step 2. Coding
Coding means highlighting sections of our text – usually phrases or sentences – and producing
shorthand labels or “codes” to describe their content.

Step 3. Generating Themes

Look over the created codes, identify patterns among them, and start producing themes.
Themes are generally broader than codes. Most of the time, you’ll combine several codes into a
single theme.
Step 4. Reviewing Themes
Make sure that themes are useful and accurate representations of the data. Return to the data
set and compare themes against it.
Are we missing anything?
Are these themes really present in the data?
What can we change to make our themes work better?

Step 5. Defining and Naming Themes

Defining themes involves formulating exactly what we mean by each theme and figuring out
how it helps us understand the data.

Naming themes involves producing a succinct and easily understandable name for each theme

Step 6. Writing Up
Write up the analysis of data.

A. Writing Up the Results Set up, Quote, Comment

Set up
Present your specific research questions one by one
(significant questions from your instrument which led to answering each specific question)

Set up
Introduce the quote by combining the idea and the situation of the one quoted
• The paragraph starts with a sentence that orients or introduces the main idea or point.
• After this, the next sentence starts to describe where the quote came from.
• When you have a quote in Filipino, which is not the main Language for the entire paper,
you should cite in the original Language.

Quote
Present the results by using direct quotation from your participants. Rather than use one quote
after another, you will need to learn which points/answers deserve direct quotations.

Comment
Talk about what is notable about the answers or answers of your other participants
Step 6: Writing Up
B. Writing Up The Discussion

• When analyzing Interviews and questionnaires, you should think about the themes that stem
from your interviews - these themes should answer your research questions.
• To write the summary, you should organize the themes without using quotes.

Interpret the results and support the themes by using the following:
• Results from similar, previous studies published in relevant journal articles
• Theories or concepts from your field (theoretical framework)
• Other relevant aspects

Quantitative Data Analysis – Descriptive and Inferential Statistics

Analyzing the Meaning of the Data and Drawing Conclusions

Descriptive Statistics
Descriptive statistics is when a researcher describes, shows, and generalizes the dataset
acquired from the sample. Through measures of central tendency, frequency distribution,
percentage count, and verbal interpretations, he can present the data in an organized way.

Common Practices in Data Presentation

Measures of Central Tendency – Mean, Median, and Mode
Frequency Distribution and Percentage Count Weighted Mean and Verbal Interpretations

Measures of Central Tendency

A measure of central tendency is a summary measure that defines the general set of data with a
single value that represents the middle of center of its distribution.

MEAN – the average

MEDIAN - the middle value
MODE – the most frequent value
Measures of Central Tendency
Example: The following are the scores of the students in ENG104 in their fourth quarter
examination: 45, 47, 47, 35, 42, 50, 50, 45, 46, 47, 39.
Find the mean, median, and mode of the dataset

Frequency Distribution and Percentage Count

Frequency distribution and percentage count work relatively to show the distribution of the
responses of the participants. They work best to demographic profiling, yes/no questions, single
or multiple response questions, and Likert scales.

Verbal Interpretations
Verbal interpretations are usually employed in questions that ask about levels of agreement or
attitude about certain indicators.

Weighted Mean and Verbal Interpretations

Weighted mean is when a researcher gives certain weights to a set of choices.

On the other hand, verbal interpretations are usually employed in questions that ask about levels
of agreement or attitude about certain indicators.

Test of Association – Pearson, Spearman, and Chi-square

Test of Association
At times, when researchers are interested on knowing if a variable affects the other, they do
correlational research. A correlation is done to assess the linear relationship of two numerical
variables.

Test of Association
What researchers always compute for is the correlation coefficient and there are different
statistical treatments employed for it. But remember that if correlation coefficient is not
applicable, then there is a statistical treatment that one could try.
Pearson Correlation Coefficient
Also known as Pearson’s R, it is the first choice a researcher can choose if his data is continuous
(interval or ratio), if that is a paired sample, and they are normally distributed.

Spearman’s Correlation
Coefficient Spearman’s correlation coefficient is a statistical measure of the strength of a
monotonic relationship between paired data which can be interval, ratio, or ordinal.

A monotonic relationship is described as on that either never increases or never decreases as its
independent variable increases.

Chi-square Test of Independence

If researchers only have categorical variables but still want to test the association of them, then
Chi-square Test of Independence is the best statistical measurement.
Chi-square Test of Independence
Unlike Pearson and Spearman that you can get the correlation coefficient of the variables, on this
type of statistical treatment, you need to check if the calculated critical value is going to be equal
or more than the critical value for the degree of freedom based on the dataset.

Test of Difference – T-Test and ANOVA

Test of Difference

When researchers are interested to see if there are differences between two or more means and
they are statistically significant, test of difference is sought.
Researchers can:

- Utilize t-test if the samples are only two

- Utilize analysis of variance if the samples are more than two.

T-test

The t-test is a basic test that is limited to two groups.

There are two types of t-tests:
- Independent T-test – When samples are not matched
- Matched-pair t-test – When samples appear in pairs.

Independent T-test
When samples are not matched, independent ttest is used.
Independent T-test

To test the hypothesis, you need to check for the degree of freedom from the given dataset. After
getting the df, you need to know the critical value based on it and compare it to the calculated t
value.

Remember that if the t value is equal or greater than the critical value, it means that there is a
significant difference between the group. You need to reject Ho .

Dependent T-test
When samples seem to look like pairs, dependent T-test shall be employed.

Analysis of Variance
If the researcher wants to compare three or more means, then analysis of variance (ANOVA) is
the most suitable statistical treatment. The ANOVA coefficient is solved through this formula:

Analysis of Variance
After getting the f value, researchers need to check if that will be equal or greater than the critical
value to see if the null hypothesis is going to be rejected or not and if the difference is going to be
significant or not. But we have two degrees of freedom. With that, remember to use the f
distribution table.