Data Analysis and

Interpretation

Dr.S. Ruban
ruban@staloysius.ac.in
 Teaching Vs Research

• Teaching without Publication is

close to a mechanical activity.
• Research without publication is
academic timidity.
• Make it Interdisciplinary and col-
laborative.
Interdisciplinary Vs Collabora-
tive
DATA
Data - a collection of facts
from which conclusions
may be drawn.
Obtaining appropriate
facts/information that is
relevant or appropriate to a
decision maker. Data con-
tain information which can
be collected from an exper-
iment, a survey, a historical
record, etc.
 Examples of DATA.

We live in a world filled with data.

 Stock prices in a daily newspaper
 Reports generated by the Bureau of the Census.
 The student record system at your school.

The challenge is not finding data, but choosing which data to use

Data is the interface between various departments in the business

 Types of Data (1)
• Primary Data.
- High Quality/Insight
- Ethnographic Research
• Secondary Data
- Online DB
- Literature reviews
• Big Data
- Volume / Velocity
- Variety / Veracity
 Types of Data (2)
• Structured Data.
- DBMS
- Format
• Unstructured Data
- Web
- Social media
• Semi structured Data
- HTML
- XML
 Types of Data (3)
• Quantitative Data.
- Numeric

• Qualitative Data
- Text
- Phrases

• Mixed Data
- Both Numbers/Text
 Quantitative data collection
methods.
• Quantitative methods are used to collect numerical or quantifiable
data.
• These can then be processed statistically to test hypotheses and gain
insights.
• Quantitative data gathering is typically aimed at measuring a particu-
lar phenomenon (e.g., the amount of awareness a brand has in the
market, the efficacy of a particular diet, etc.)
• Or in order to test hypotheses (e.g., social media marketing cam-
paigns increase brand awareness, eating more fruits and vegetables
leads to better physical performance, etc.).
Eg: Surveys, Observations, Database.(climate/Healthcare)
 Qualitative data collection
methods
• Analyzing qualitative data is important for describing a phenomenon
(e.g., the requirements for good teaching practices), which may lead to
the creation of propositions or the development of a theory.
• Behavioral data, transactional data, and data from social media monit-
oring are examples of different forms of data that can be collected qual-
itatively.
Examples:
 Observational research,
 Employ tools such as audio and video recorders,
 Notebooks for writing field notes,
 Cameras for taking photographs.
 As long as products of such tools can be analyzed, those products can be incor-
porated into a study's data collection.
 Mixed methods research.
Employs multiple data collection methods, including qualitative and quantitative
data, along with multiple tools to study a phenomenon from as many different
angles as possible.

Example:
Researcher incorporate direct observation, interviews, focus group sessions, and
document collection in their data collection process to produce the most contex-
tualized data for their research.
 Data Collection.

 Collecting the right data.

Eg: it's important to collect data that is relevant for answering your Research
Question.
: what factors do people consider when buying a car?.
….
Examples:
 Responses to a survey about product satisfaction
 Interviews with students about their career goals
 Reactions to an experimental vitamin supplement regimen
 Observations of workplace interactions and practices
 Focus group data about customer behavior
 New forms of data collection
• External data sources such as social media data and big data.
• Climatic Data.
• Digital Forms(online Surveys/Questionaires)
- Google Form
- Jot Form
- Zoho Form.
• CCTV / Sensors /Wearable devices.
• Data Repositories.
 Data quality issues.
Data quality is a crucial consideration when gathering informa-
tion. Your analysis may depend on capturing the fine-grained
details that some data collection tools may miss.
Eg: Smart phone camera / Professional Camera
 Data Integrity. (Ethics/credible)
 Transparency. (where data came/How)
 Subjectivity (Do peoples perspective represent Collected Data)
 Validity.
 Reliability (consistency)
 Enhancing data quality.

1. Triangulation: This involves using multiple data sources, methods, or

researchers to gather data about the same phenomenon.
2. Member checking: This involves returning the findings to the parti-
cipants to check if the interpretations accurately reflect their experi-
ences or perceptions.
3. Thick description: Providing detailed accounts of the context, interac-
tions, and interpretations in the research report can allow others to un-
derstand the research process better.
4. Audit trail: Keeping a detailed record of the research process, decisions,
and reflections can increase the transparency and coherence of the
study.
 What fields use qualitative research?

Some of the key fields that utilize qualitative research include:

1. Psychology: .
2. Sociology:
3. Anthropology:
4. Education:
5. Health and medicine: .
6. Business and management:
7. Communication studies:
8. Social work:
9. Political science:
10. Environmental studies:
 Purposes of a Qualitative Re-
search.
• Generating new theory
• Developing or challenging existing theory
• Proposing practical implications
• Enhancing understanding and empathy
• Informing mixed-methods research
 Some Examples of Qualitative
Research
• Exploring the lived experiences of refugees
• Understanding the dynamics of online communities:
• Examining the impact of gentrification on local communities:
• Studying the career trajectories of women in STEM fields:
• Evaluating the effectiveness of a mental health intervention:
• Investigating the role of social media in political activ-
ism:
 Why We do Qualitative Research

• Dissertations and theses:

• Journal articles:
• Market research reports:
• Needs assessment reports:
• Other formats: In addition to the aforementioned formats, qualitative research
findings can also be reported in conference presentations, white papers, policy
briefs, blog posts, or multimedia presentations.
• Mini projects / Major projects.
• Student Projects
 Qualitative data
• Rather than focusing on quantities or measurements, qualitative data
aims to understand the intricate nature of phenomena, uncovering the
'why' and 'how' rather than 'how much.'
• It often includes words, descriptions, visual images, symbols, or per-
sonal narratives. This data is typically unstructured or semi-structured,
featuring open-ended responses that allow for expressive, detailed, and
context-specific responses. It explores subjective experiences, individual
perceptions, emotions, beliefs, and behaviours in social and cultural
contexts.
• Qualitative data can reveal patterns, themes, and categories that reflect
the depth of participants' experiences and the structures of their world.
It can potentially capture unforeseen phenomena, leading to new in-
sights or theories.
 The qualitative data collection
methods(1) .
1. Case study research
• The case study research approach provides a rich, detailed analysis of a specific
'case,' which can be a single individual, group, event, or organization.
• Researchers employing this method gather data using multiple sources, such
as interviews, observations, and documents, which offer a more complete picture
of the case under study.
2.Ethnographic research
• Ethnographic research is a method deeply rooted in cultural anthropology, where
the researcher immerses themselves in the everyday life of the group or commu-
nity they are studying.
• It involves long-term engagement and close observation of the group, often
through participation in their activities. The primary aim is to gain an insider's per-
spective of the group's social dynamics, beliefs, rituals, and behaviors.
 The qualitative data collection
methods(2) .
3. Grounded theory research
• Grounded theory research is a qualitative method that seeks to develop a theory
rooted in the data.
• The key feature of this method is its systematic procedure of data collection and
analysis, which is designed to facilitate the development of theory that emerges
from the data.
4. Narrative research
• Researchers who focus on narratives are centered on the stories that individuals tell
about their experiences and life events. These narratives offer a window into indi-
viduals' perspectives, providing insights into their feelings, motives, and actions.
• The second part of the narrative research process is the interpretation of these sto-
ries. Researchers looks for patterns and themes that reveal more profound mean-
ings.
 The qualitative data collection
methods(3) .
5. Phenomenological research
• Focuses on understanding individuals' lived experiences concerning a particular
phenomenon.
• A phenomenological study involves detailed interviews, observations, or diary en-
tries, allowing the researcher to delve into the intricate details of people's experi-
ences and feelings.
6. Action research
• It is a collaborative, participatory approach to research that aims to solve real-world
problems. In this approach, researchers work closely with community members or
stakeholders, who are actively involved in all stages of the research process, from
identifying the problem to implementing and evaluating the solution.
• This method is usually employed in educational, organizational, or community set-
tings.
 Which approach to qualitative meth-
ods is best?.
Choosing the best approach to qualitative research depends on various factors,
including the nature of the research question, the context of the study, the re-
searcher's familiarity with the approach, and ethical considerations. Here are
some guiding questions:

•What is the main purpose of the study?

•What kind of data is needed to effectively answer the research question?
•What is the context in which the research is being conducted?
•What are the ethical considerations associated with each approach?
•Which approach aligns best with the researcher's skills and interests?
 Most common qualitative research
methods.(1)
Any research method that produces unstructured data can be con-
sidered a qualitative research method.

1. Observations
The simplest way to study a phenomenon is to look at it. Research
conducted through direct observation involves collecting data
in field notes, recordings of audio and video, and images for data
analysis.
 Most common qualitative research
methods.(2)
Any research method that produces unstructured data can be considered a
qualitative research method.

2. Interviews:
Interviews are a fundamental method in qualitative research, al-
lowing researchers to gather in-depth information about individu-
als' thoughts, feelings, experiences, and interpretations. Interviews
can take various forms, from highly structured with predetermined
questions, to semi-structured with some guidance,
to unstructured or 'open-ended'
 Most common qualitative research
methods(3).
Any research method that produces unstructured data can be considered a
qualitative research method.
3. Focus groups
• It consists of a group of participants collectively discussing a
topic, speaking among themselves even more than they might
speak to the researcher or focus group moderator.
• The aim is to inquire about people's perceptions, opinions, be-
liefs, and attitudes towards the topic of study, which could be a
feature of social life, such as body art or a specific product, such
as market research for a new campaign
 Most common qualitative research
methods(4).
Any research method that produces unstructured data can be considered a
qualitative research method.
4.Surveys
• Surveys in qualitative research often differ from those in quanti-
tative research, because an important part of these surveys is
the collection of open-ended responses that allow participants
to provide detailed responses in their own words. .
• surveys can provide valuable insights into participants' per-
spectives and experiences.
 Most common qualitative research
methods(5).
Any research method that produces unstructured data can be considered a qualitative
research method.
5.Document Collection
• It is a versatile method in qualitative research that involves the analysis of
existing texts.
• These texts can come in a variety of forms, such as official documents,
newspapers, letters, diaries, transcripts, literary works, photographs, or even
digital content like social media posts, blogs, and websites.
• The content of these documents can provide valuable insights into the phe-
nomenon under investigation, contextual factors, and historical trends.
 Most common qualitative research
methods(6).
6.Other Research Methods:
• Participant observation - This is a method used to observe behaviours, interactions,
and events as they naturally occur, leading to a deep understanding of the group's
dynamics.
• Visual methods - These involve the use of visual materials, such as photographs,
drawings, videos, or maps. It offers unique insights and are particularly useful when
exploring topics that are difficult to express in words.
• Diaries and journals - In this method, participants are asked to keep a record of their
experiences, thoughts, and feelings over a certain period. These records can provide
rich, detailed, and longitudinal data. For example, diaries and journals are often used
in health and social care research to study people's daily lives, experiences of illness,
or caring roles.
• Life history - Collecting life histories is a type of narrative research where participants
are asked to tell their life story or focus on a particular aspect or period of their life
 How do I choose the best qualitative re-
search method?.

• Think about what you want to study concerning a particular

topic or concept.
• keep in mind that the use of multiple qualitative research
methods can provide a deeper exploration of a concept than
the use of one method alone.
• Any study first begins with the research question and topic
Main steps and considerations in an-
alyzing data(1)
1.Organizing the data (CASE STUDY)
The first step in the analysis is organizing the data. This in-
volves sorting the data into manageable sections, often ac-
cording to the data source or the theme.
2. Categorizing and coding the data
Once the data is organized, the next step is to categorize or
code the data. This involves identifying common themes,
patterns, or concepts in the data and assigning codes to rel-
evant data segments. Coding can be done manually or with
the help of software tools.
 Main steps and considerations in an-
alyzing data (2)
3. Identifying patterns and themes
After coding the data, the researcher looks for patterns or themes in the coded
data. This involves comparing and contrasting the codes and looking for relation-
ships or patterns among them.
4. Interpreting the data
This involves explaining what the patterns or themes mean in the context of the
research question and the case. This interpretation should be grounded in the
data, but it can also involve drawing on theoretical concepts or prior research.
5. Verification of the data
The last step in the analysis is verification. This involves checking the accuracy
and consistency of the analysis process and confirming that the findings are sup-
ported by the data.
Quantitative Data.
 Quantitative Data.
Quantitative data/ Numerical data: These are data values
that are numeric which are quantifiable. Quantitative data
indicate either how many or how much. Quantitative data
are always numeric.
For example:
• The heights/weights /scores of basketball players
• Starting salary of an MBA graduate
• Fuel efficiency of cars
• Income of a family
• population of a country
Data
Measurement Scale.
 Nominal(1/2)

NOMINAL SCALE :
• This is the lowest level of measurement. Here, numbers are assigned for the purpose of identifica-
tion of the objects. It is simply a system of assigning number symbols to events in order to label
them.
• In the nominal scale there is a strict one-to-one correspondence between the numbers and the
objects. Each number is assigned to only one object and each object has only one number as -
signed to it.
• Nominal Scale is widely used and simple to use.
• Nominal scale measurements are used for identifying food habits (vegetarian or non-vegetarian),
gender (male/female), caste, respondents, brands, attributes, stores, the players of a hockey team
and so on.
• NOTE: The assigned numbers cannot be added, subtracted, multiplied or divided.
• The only arithmetic operations that can be carried out are the count of each category. Therefore,
a frequency distribution table can be prepared for the nominal scale variables and mode of the
distribution can be worked out. One can also use chi-square test and compute contingency coeffi-
cient using nominal scale variables.
 Nominal(2/2)

NOMINAL SCALE :

Example: Have you ever visited Bangalore?

Yes-1 No-2
‘Yes’ is coded as ‘One’ and ‘No’ is coded as ‘Two’. The numeric attached to the answers has no meaning, and is
a mere identification. If numbers are interchanged as one for ‘No’ and two for ‘Yes’, it won’t affect the an-
swers given by respondents. The numbers used in nominal scales serve only as labels/tags for identifying and
classifying objects with a strict one-to-one correspondence between the numbers and the objects.

Common Example:
• Assigning the numbers of football players in order to identify them.
• University Registration numbers assigned to students,
• Brand numbers,
• Store types,
 ORDINAL SCALE(1/2)
• The Ordinal scale is used for ranking in most market research studies. It is a ranking scale
in which numbers are assigned to objects to indicate some characteristic. Ordinal scales
are used to ascertain the consumer perceptions, preferences etc. It is an extension of
nominal scale with an indicator of the order indicating relative position.

Example: quality ranking, rankings of teams in tournament. Market position, social class etc.
• In the ordinal scale, the assigned ranks cannot be added, multiplied, subtracted or di-
vided.
• One can compute median, percentiles and quartiles of die distribution. The other major
statistical analysis which can be carried out is the rank order correlation coefficient, sign
test.
• As the ordinal scale measurement is higher than the nominal scale measurement, all the
statistical techniques which are applicable in the case of nominal scale measurement can
also be used for the ordinal scale
 ORDINAL SCALE(2/2)
Example 1: Rank the following attributes while choosing a restau-
rant for dinner. The most important attribute may be ranked one,
the next important may be assigned a rank of 2 and so on.

Attribute Rank
Food quality
Prices
Menu variety
Ambience
Service
 INTERVAL SCALE(1/2)
• Interval scale is more powerful than the nominal and ordinal scales. A scale in which num-
bers are used to rate objects such that numerically equal distances on the scale represent
equal distances in the characteristic being measured.
• Interval scales can have arbitrary zero, but not possible to determine what is absolute zero
or unique origin
• The primary limitation of this scale is lack of true zero; The most common example of the in-
terval scale data is the relationship between Celsius and Fahrenheit temperature. Suppose if
one say that an increase in temperature from 30 0 to 400 involves the same increase in tem-
perature as an increase from 600 to 700,but one cannot tell that 600 is as twice warmer than
300, because both are dependent on the fact that the zero on the scale is set arbitrary as
freezing point of water.
• The numbers on this scale can be added, subtracted, multiplied or divided. One can com-
pute arithmetic mean, standard deviation, correlation coefficient and conduct a t-test, Z-
test, regression analysis and factor analysis.
 INTERVAL SCALE(2/2)
As the interval scale data can be convened into the ordinal and the nominal scale data, therefore all the tech-
niques applicable for the ordinal and the nominal scale data can also be used for interval scale data.
Example 1: Suppose we want to measure the rating of a refrigerator using interval scale. It will appear as fol-
lows:
1. Brand name Poor ————————- Good
2. Price High ————————- Low
3. Service after-sales Poor ————————- Good
4. Utility Poor ————————- Good
The researcher cannot conclude that the respondent who gives a rating of 6 is 3 times more favourable to-
wards a product under study than another respondent who awards the rating of 2.
Example 2: How likely are you to buy a new designer carpet in the next six months?

Very unlikely Unlikely Neutral Likely Very likely

Scale A 1 2 3 4 5
Scale B 0 1 2 3 4
Scale C -2 -1 0 1 2
 RATIO SCALE
• These have all properties of nominal, ordinal and interval scales and in addition absolute or
true zero measurement. In ratio scales we can identify, classify the objects, rank the objects,
and compare intervals or differences. Ratio scales represents the actual amounts of variables.

Example: weight, height, distance, Age, income, market shares costs, sales etc.
• Generally all statistical techniques, manipulations that one can carry out with real numbers
are carried out by ratio scale values. It facilitates the comparison which is not possible in other
scales. Multiplication and division can use with this scale but not with other scale. Compared
to others relevant information is obtained increasingly.
• Descriptive statistics like Geometric mean, harmonic mean can be used and inferential statis-
tics like coefficient of variation is used.
• With the help of Ratio scale length, weight or distance can be measured. In this scale, it is pos-
sible to say, how many times greater or smaller one object is being compared to the other.
• Example: Sales this year for product A are twice the sales of the same product last year.
 Statistical Implications

Scale Number Order Distance True Zero Examples

Nominal YES NO NO NO Color, Gender, Ethnicity, Country

YES
Ordinal YES NO NO Rating scales, Rank orders

YES YES NO
YES
Interval Time of day, Year, IQ, Likert scales
YES YES
YES
Ratio YES Age, Height, Weight, Rates
STATISTICAL TECHNIQUES USED FOR MEA-
SUREMENT SCALES

Scale Basic Common Marketing Permissible Statistics

Characteristics Examples Examples Descriptive Inferential
Nominal Numbers identify Social Security Brand nos., store Percentages, Chi-square,
& classify objects nos., numbering types mode binomial test
of football players
Ordinal Nos. indicate the Quality rankings, Preference Percentile, Rank-order
relative positions rankings of teams rankings, market median correlation,
of objects but not in a tournament position, social Friedman
the magnitude of class ANOVA
differences
between them
Interval Differences Temperature Attitudes, Range, mean, Product-
between objects (Fahrenheit) opinions, index standard moment
Ratio Zero point is fixed, Length, weight Age, sales, Geometric Coefficient of
ratios of scale income, costs mean, harmonic variation
values can be mean
compared
Data Analysis Strategy
Descriptive Data Analysis(1/3)
Descriptive Data Analysis(2/3)
Descriptive Data Analysis(3/3)

BIVARIATE STATISTICS
BIVARIATE STATISTICS MEASURE OF
ASSOCIATION
Multivariate Techniques
 CODING AND CATEGORING QUALITA-
TIVE DATA.

Question: How many hours have you spent sitting in front of

Excel spreadsheets trying to find new insights from customer
feedback?
• You know that asking open-ended survey questions gives
you more actionable insights than asking your customers
for just a numerical Net Promoter Score (NPS). But when
you ask open-ended, free-text questions, you end up with
hundreds (or even thousands) of free-text responses.
• How can you turn all of that text into quantifiable, applic-
able information about your customers’ needs and expecta-
tions? By coding qualitative data.
 What is coding in qualitative re-
search?.
• Coding is the process of labeling and organizing your qualitative data to
identify different themes and the relationships between them.
• When coding customer feedback, you assign labels to words or phrases
that represent important (and recurring) themes in each response. These
labels can be words, phrases, or numbers; we recommend using words or
short phrases, since they’re easier to remember, skim, and organize.
• Coding qualitative research to find common themes and concepts is part
of thematic analysis. Thematic analysis extracts themes from text by ana-
lyzing the word and sentence structure.
 Automated vs. Manual coding of
qualitative data.

Methods of coding qualitative data fall into two categories: automated cod-
ing and manual coding.
• You can automate the coding of your qualitative data with thematic anal-
ysis software. Thematic analysis and qualitative data analysis software
use machine learning, artificial intelligence (AI), and natural language
processing (NLP) to code your qualitative data and break text up into
themes.
• Thematic analysis software is autonomous, which means…
• You don’t need to set up themes or categories in advance.
• You don’t need to train the algorithm — it learns on its own.
• You can easily capture the “unknown unknowns” to identify themes you
may not have spotted on your own.
 INTRODUCTION TO STATISTICAL SOFTWARE FOR
QUANTITATIVE ANALYSIS.

Key Functions: Statistical software typically offers the following key func-
tions:
• Data Import and Management: Importing and organizing data from various
sources.
• Descriptive Statistics: Calculating basic statistics like mean, median, and
standard deviation.
• Inferential Statistics: Conducting hypothesis tests, confidence intervals, and
ANOVA.
• Regression Analysis: Modeling relationships between variables.
• Data Visualization: Creating charts, graphs, and plots to represent data visu-
ally.
• Time Series Analysis: Analyzing data points collected over time.
• Machine Learning: Implementing predictive modeling and classification
 Common Statistical Software's
• R: An open-source language and environment for statistical computing
and graphics.
• Python: A versatile programming language with libraries like NumPy,
SciPy, and pandas for data analysis.
• SPSS (Statistical Package for the Social Sciences): Widely used in so-
cial sciences and market research.
• SAS (Statistical Analysis System): Common in healthcare, finance, and
government sectors.
• STATA: Popular for economics and social sciences research.
• JMP: Primarily used for dynamic data visualization and exploratory
data analysis.
• JAMOVI
 Quantitative analysis Workflow.
• Data Collection: Gather and prepare data from various sources.
• Data Cleaning: Remove duplicates, handle missing values, and standard-
ize data.
• Data Exploration: Visualize and understand the data using summary stat-
istics and visualizations.
• Statistical Analysis: Apply appropriate statistical tests and models based
on research questions.
• Interpretation: Analyze results and draw meaningful conclusions.
• Reporting: Communicate findings through reports and visual presenta-
tions.
STRATEGIES FOR INTERPRETING FINDINGS FROM BOTH
QUALITATIVE AND QUANTITATIVE DATA

1. Triangulation:
2. Thematic Analysis:
3. Integration Matrix:
4. Complementary Findings:
5. Mixed-Methods Typology:
6. Theory Integration:
7. Participant Validation:
8. Reflexivity:
9. Clear Reporting:
10. Peer Review:
Moving Ahead
Research Lab with Health Data…
 Thank
You
Contact : Dr. Ruban S, HOD,
Department of M.Sc. Software Technology

9741965134

ruban@staloysius.ac.in