KARPAGA VINAYAGA

COLLEGE OF ENGINEERING AND TECHNOLOGY

(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

UNIT-2 DATA COLLECTION AND SOURCES

 Measurements
 Scales
 Questionnaires & Instruments
 Sampling Methods
 Data-Preparing, Exploring, examining, Displaying

 Measurement:

Definition:

 Measurements refers to the process of assigning numerical values /labels to the observed
phenomena called variables
 It enables researchers to quantify and analyze the data and it involves in facilitating the
investigation of relationship, patterns with in a study.

There are four main types of measurements:

 Nominal Measurement:
 Ordinal Measurement
 Interval Measurement:
 Ratio Measurement:

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

Nominal Measurement:

 Nominal measurements involve the assignment of categories or labels to items or

observations without any inherent order or ranking.
 These categories are mutually exclusive, meaning that each item or observation can
only belong to one category.
 Examples include gender (male, female), colors (red, blue, green), and types of fruit
(apple, banana, orange).

GENDER COLORS FRUITS

BLUE BANANA
FEMALE RED APPLE
MALE

GREEN ORANGE

(Its categorizing data into distinct group with no inherent order)

Ordinal Measurement:

 Ordinal measurements involve the categorization of items or observations into ordered

groups or classes.
 While there is a relative order between categories, the intervals between them are not
necessarily uniform or meaningful.
 Examples include rankings (1st, 2nd, 3rd), education levels (high school, college,
graduate school), and customer satisfaction ratings (poor, fair, good, excellent).

I)Educational Level: High School Diploma < Some College < Bachelor's Degree <
Master's Degree < Doctorate

II)Customer Satisfaction Ratings:Very Dissatisfied < Dissatisfied < Neutral <

Satisfied < Very Satisfied

III)Movie Ratings:One Star < Two Stars < Three Stars < Four Stars < Five Stars

 Data’s are categorized into ordered groups/ranks but interval between them are not
uniform, it tells which is greater >,< lesser but not how much .

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

Interval Measurement:

 Interval measurements involve assigning scores or values to items or observations where

the intervals between adjacent values are equal and meaningful.
 However, there is no true zero point, meaning that it does not represent the absence of
the measured attribute.
 It has ordered categories with uniform intervals between them but there is no true 0 point.

 Examples include temperature in Celsius or Fahrenheit, IQ scores, and Likert scale

ratings.

I)Temperature (in Celsius or Fahrenheit):

The difference between 20°C and 30°C is the same as the difference between 30°C
and 40°C. However, 0°C does not represent the absence of temperature.
II) IQ Scores:
An IQ score of 100 is considered to be the same distance from 90 as it is from 110.
However, an IQ score of 0 does not mean a complete absence of intelligence.
III)Likert Scale (with a neutral point):
On a scale of 1 to 7, where 4 represents "Neutral" or "Neither Agree nor Disagree,"
the difference between "Agree" (5) and "Strongly Agree" (7) is considered the same
as the difference between "Disagree" (2) and "Strongly Disagree" (1).

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

Ratio Measurement:

 Ratio measurements have all the characteristics of interval measurements but also
include a true zero point, which signifies the complete absence of the attribute being
measured.
 This allows for meaningful statements about the ratio or proportion between different
values.
 Examples include height, weight, age, income, and number of items.

I)Height: A person who is 180 cm tall is twice as tall as a person who is 90 cm tall,
because there is a true zero point (i.e., no height).
II)Weight: If one person weighs 60 kg and another weighs 30 kg, we can say that the
first person weighs twice as much as the second person, because there is a true zero
point (i.e., no weight).
III)Age:A person who is 40 years old is twice as old as a person who is 20 years old,
because there is a true zero point (i.e., birth).
IV)Income:If one person earns $50,000 per year and another earns $25,000 per year,
we can say that the first person earns twice as much as the second person, because
there is a true zero point (i.e., no income).
V)Number of Children:A family with 4 children has twice as many children as a
family with 2 children, because there is a true zero point (i.e., no children).

Advantages and Disadvantages of using measurements in research:

Advantages:
1. Precision and Accuracy: Measurements provide a precise and accurate way to quantify
variables. This allows for more rigorous and reliable analysis of data.
2. Quantification of Variables: It enables researchers to convert abstract concepts or
characteristics into numerical values, making them amenable to statistical analysis.
3. Comparability: Measurements allow for meaningful comparisons between different
individuals, groups, or situations. This is particularly important for drawing valid
conclusions from the data.
4. Objectivity: Objective measurements can reduce the potential for bias in data collection,
as they are based on standardized procedures and instruments.
5. Facilitates Replication: Clear and standardized measurements make it easier for other
researchers to replicate a study, which is a fundamental aspect of scientific research.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

6. Statistical Analysis: Measurements provide the necessary data for various statistical
techniques, allowing for the testing of hypotheses and drawing of meaningful
conclusions.
7. Longitudinal Studies: Measurements allow for the tracking of changes over time, which
is important for studies involving trends, development, or interventions.

Disadvantages:
1. Measurement Error: Despite efforts to ensure accuracy, there is always the possibility
of measurement error. This can be due to instrument limitations, observer bias, or
respondent factors.
2. Subjectivity in Some Cases: In certain fields or with certain types of measurements
(e.g., subjective assessments of pain or emotions), there may be a degree of subjectivity
that can introduce potential bias.
3. Inadequate Instruments: If the chosen measurement instrument is not appropriate or
well-validated for the specific variable being studied, it can lead to unreliable or invalid
results.
4. Cost and Time Intensive: Developing, testing, and administering measurements can be
resource-intensive, especially if specialized instruments or equipment are required.
5. Difficulty in Measuring Abstract Constructs: Some variables, like personality traits or
complex psychological constructs, can be challenging to measure accurately due to their
abstract and multifaceted nature.
6. Limited Scope: Measurements are often limited to what can be quantified, which may
not capture the full complexity or richness of certain phenomena.
7. Ethical Considerations: In some cases, the process of measurement may raise ethical
concerns, especially if it involves sensitive or personal information.
8. Potential for Reductionism: Relying solely on measurements can lead to a reductionist
approach, potentially overlooking qualitative or contextual aspects of the phenomenon
under study.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

 Scales:
 A "scale" refers to a set of standardized procedures or tools used to measure or assess
specific attributes, characteristics, or constructs of interest. Scales provide a systematic
and structured way to collect data in a reliable and consistent manner.
 They are designed to ensure that the data collected is valid, meaning it accurately reflects
the concept being measured. Scales are used to quantify or categorize various
psychological, social, or physical phenomena.
 They help researchers obtain numerical or categorical data that can be analyzed
statistically. The choice of a specific scale depends on the nature of the variable being
studied and the research objectives.
Types of scales:
1. Nominal Scale: Involves assigning categories or labels without any inherent order or ranking
(e.g., gender, colors).
2. Ordinal Scale: Categorizes items into ordered groups or classes, with a relative order
between categories, but intervals between them are not necessarily uniform or meaningful
(e.g., rankings, Likert scales).
3. Interval Scale: Assigns scores where the intervals between adjacent values are equal and
meaningful, but there is no true zero point (e.g., temperature in Celsius or Fahrenheit, IQ
scores).
4. Ratio Scale: Has all the characteristics of interval measurements but includes a true zero
point, signifying the complete absence of the attribute being measured (e.g., height, weight,
age).
5. Likert Scale: A commonly used measurement tool in social sciences, it assesses attitudes,
opinions, or perceptions. Respondents indicate their level of agreement or disagreement with
a series of statements using a predetermined scale (e.g., strongly agree, agree, neutral,
disagree, strongly disagree).
6. Bipolar Scale: Similar to Likert scales, but it includes both positive and negative statements.
Respondents indicate their level of agreement or disagreement on a continuum between the
positive and negative extremes. This type of scale provides a nuanced understanding of
respondents' attitudes or opinions by allowing them to express a spectrum of feelings or
perceptions, rather than just one-sided agreement or disagreement. It is often used in areas
where it's important to capture both positive and negative aspects of a construct.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

Example: Job Satisfaction Scale

Please indicate your level of agreement with the following statements:

A. I find my work enjoyable and fulfilling.
Strongly Disagree | Disagree | Neutral | Agree | Strongly Agree

B. I experience a sense of accomplishment in my role.

Strongly Disagree | Disagree | Neutral | Agree | Strongly Agree

C. I feel frustrated or dissatisfied with my job.

Strongly Disagree | Disagree | Neutral | Agree | Strongly Agree

7.Visual Analog Scale (VAS):

 This is a continuous scale that allows respondents to mark a position along a line to
represent their subjective feelings or perceptions about a particular characteristic. It is
often used for pain assessment, mood evaluation, and other subjective experiences.
 The Visual Analog Scale (VAS) is a measurement instrument used in healthcare to assess
subjective characteristics or attitudes that cannot be directly measured. It is a
psychometric response scale often used in surveys, questionnaires, and clinical
assessments to quantify the intensity or magnitude of a participant's feelings or
experiences.

Here's how it works:

Format: A VAS typically consists of a horizontal line, usually 10 centimeters (100
millimeters) in length, with anchor statements at each end. The left end is labeled with the
lowest possible rating (e.g., "No Pain" or "Not at all"), and the right end is labeled with the
highest possible rating (e.g., "Worst Pain Imaginable" or "Extremely").

Instructions: Participants are asked to place a mark on the line to indicate their level of
agreement or intensity with a specific statement or question. They do this by drawing a
vertical line perpendicular to the VAS line at the point that best represents their response.
Measurement: The distance from the left end of the line to the participant's mark is then
measured in millimeters. This measurement provides a numerical value representing the
participant's response.
Interpretation: The resulting value can be used for statistical analysis or to track changes
over time. For example, in pain assessment, a higher value indicates more severe pain, while
a lower value indicates less pain.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

Advantages:
1. Quantification: Scales allow researchers to assign numerical values to subjective or
abstract concepts, making them amenable to statistical analysis.
2. Precision: Well-constructed scales can provide precise measurements, which can
enhance the validity and reliability of the data collected.
3. Comparability: Scales enable meaningful comparisons between different individuals,
groups, or situations. This is crucial for drawing valid conclusions and making
generalizations.
4. Objective Data Collection: Scales can reduce the potential for bias in data collection
compared to unstructured or open-ended questions. They provide a standardized way to
gather information.
5. Efficiency: Scales can be more time-efficient than other methods, especially when
dealing with large samples or when conducting repeated measurements.
6. Facilitates Statistical Analysis: Data from scales can be easily analyzed using various
statistical techniques, allowing researchers to test hypotheses and draw meaningful
conclusions.
7. Ease of Data Processing: Numerical data from scales can be processed and analyzed
using software, which can streamline data management and analysis.
8. Clear Communication of Results: The use of scales allows for clear and transparent
reporting of findings, which enhances the transparency and replicability of research.

Disadvantages:
1. Limited to What Can be Measured: Scales are designed to measure specific attributes,
which means they may not capture the full complexity or richness of certain phenomena.
2. Potential for Response Bias: Respondents may not always provide accurate or truthful
responses, especially if they feel pressured to conform to certain norms or expectations.
3. Validity Concerns: The validity of a scale depends on how well it measures the
intended construct. Poorly designed or inappropriate scales can lead to unreliable or
invalid results.
4. Difficulty in Developing Valid Scales: Creating a valid and reliable scale requires
expertise in survey design and a thorough understanding of the construct being measured.
5. Cultural and Contextual Sensitivity: Some scales may not be applicable or valid across
different cultural or linguistic contexts, potentially leading to biased results.
6. Potential for Fatigue or Respondent Burden: Lengthy or complex scales may lead to
respondent fatigue, which can affect the quality of responses.
7. Over-Reliance on Quantitative Data: Relying solely on scales may lead to an
overemphasis on quantitative data, potentially overlooking qualitative or contextual
aspects of the phenomenon under study.
8. Ethical Considerations: In some cases, the content of scales or the process of
measurement may raise ethical concerns, particularly when dealing with sensitive or
personal information.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

 Questionnaires & Instruments:

 A questionnaire is a research instrument used to collect data from individuals or

respondents in a standardized and structured manner.
 It consists of a set of questions or items designed to gather specific information about a
particular topic or set of topics.
 Questionnaires are widely used in various fields such as psychology, sociology,
healthcare, market research, education, and more.

Types of Questionnaires:

1. Structured Questionnaires
2. Semi-Structured Questionnaires
3. Unstructured Questionnaires

1.Structured Questionnaires:
i)Closed-Ended Questions: These are questions that provide respondents with a set of
predefined response options. Common types include:
ii)Multiple-Choice Questions: Respondents choose one or more options from a list of
possible answers.
iii)Likert Scale Questions: Respondents indicate their level of agreement or disagreement
with a statement on a scale (e.g., from "Strongly Disagree" to "Strongly Agree").
iv)Rating Scale Questions: Respondents provide a rating (e.g., on a scale from 1 to 10) for a
statement or characteristic.
v)Dichotomous Questions: These have only two possible responses (e.g., Yes/No).
vi)Semantic Differential Questions: Respondents rate an object, concept, or event on a set of
bipolar adjectives (e.g., happy-unhappy, satisfied-unsatisfied).
vii)Ranking Questions: Respondents prioritize items based on a specific criterion.
2.Semi-Structured Questionnaires:
These questionnaires combine closed-ended questions with some open-ended
questions. They provide a mix of structured response options along with opportunities for
participants to provide their own detailed responses.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

3.Unstructured Questionnaires:
1.Open-Ended Questions: These questions do not provide predefined response options.
Respondents provide their own answers in their own words. This allows for more in-depth
and qualitative insights.
Components of a Questionnaire:
Introduction:
This section includes information about the purpose of the questionnaire, any instructions for
respondents, and a statement about confidentiality and anonymity.
Demographic Information:
This section collects basic information about the respondent, such as age, gender, education
level, occupation, etc.
Main Body:
This contains the core questions related to the research objectives. It's organized in a logical
and coherent sequence.
Closing Statement:
This section typically thanks respondents for their participation and may provide any
necessary follow-up instructions.
Guidelines for Designing a Questionnaire:
Clarity and Simplicity: Questions should be clear, concise, and easily understood by
respondents.
Avoid Leading Questions: Questions should be neutral and avoid wording that might
influence respondents' answers.
Logical Flow: Arrange questions in a logical order. Start with general questions and gradually
move to more specific or sensitive ones.
Avoid Double-Barreled Questions: Avoid questions that ask about two different things at once.
Piloting and Pretesting: Before administering the questionnaire on a larger scale, pilot it with
a small group to identify and rectify any issues.
Ethical Considerations: Obtain informed consent, ensure confidentiality, and avoid sensitive
or leading questions.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

Advantages:
1. Efficient Data Collection: Questionnaires allow for the efficient collection of data from
a large number of participants, making them particularly useful for studies with a large
sample size.
2. Standardization: Questions are presented in a standardized format, ensuring that all
respondents receive the same set of questions in the same way. This reduces potential
sources of bias.
3. Anonymity and Privacy: Respondents may feel more comfortable providing sensitive
or personal information in a self-administered questionnaire compared to face-to-face
interviews.
4. Cost-Effective: Compared to other data collection methods like interviews or
observations, administering questionnaires can be more cost-effective, especially when
using online platforms.
5. Flexibility in Administration: Questionnaires can be administered through various
means, including in-person interviews, phone surveys, online surveys, and paper-based
forms, making them adaptable to different research contexts.
6. Structured Format: The structured format of questionnaires provides clear response
options, making it easier for respondents to provide accurate and consistent answers.
7. Quantifiable Data: Responses from closed-ended questions in questionnaires are easily
quantifiable, allowing for statistical analysis and comparisons.
8. Longitudinal Studies: Questionnaires are well-suited for longitudinal studies where data
needs to be collected at multiple points in time.

Disadvantages:
1. Response Bias: Respondents may not always provide accurate or truthful responses due
to social desirability bias, the desire to please, or other factors.
2. Limited Depth of Information: Questionnaires may not allow for the in-depth
exploration of complex topics compared to qualitative methods like interviews or focus
groups.
3. Lack of Clarification: Respondents may misinterpret questions or require clarification,
but in a self-administered questionnaire, they don't have the opportunity to seek
clarification.
4. Limited to Closed-Ended Questions: While questionnaires can include open-ended
questions, they are often more structured, which may limit the range of responses
compared to more flexible methods like interviews.
5. Difficulty in Developing Valid Questions: Crafting clear, unbiased, and valid questions
requires expertise in survey design and a thorough understanding of the research topic.
6. Sampling Issues: If the sample is not representative of the population of interest, the
findings may not be generalizable.
7. Overlooking Unique Cases: Standardized questionnaires may not capture the unique
experiences or perspectives of some individuals or groups.
SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

 Sampling Methods:
Definition:

 Sampling methods are techniques used by researchers to choose a smaller group of

individuals or items from a larger population.
 This smaller group, known as the sample, is studied in detail to make conclusions about the
entire population.
 Different sampling methods have specific rules for selection, and they are chosen based on
the research goals and characteristics of the population being studied.

1.Probability sampling:
 Probability sampling is a technique in research methodology that involves selecting a
sample from a population in a way that each individual or item in the population has a
known and equal chance of being chosen.
 This method ensures that the sample is representative of the larger population, allowing
for valid statistical inferences.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

Key characteristics of probability sampling include:

 Random Selection: Individuals or items are chosen entirely at random, without any bias
or preference.
 Equal Probability of Selection: Each element in the population has an equal chance of
being selected. This ensures fairness and reduces potential sources of bias.
 Known Sampling Error: With probability sampling, it's possible to estimate the degree
of sampling error, which is the difference between sample estimates and population
parameters.

Common types of probability sampling methods include:

1. Simple Random Sampling: Involves randomly selecting individuals or items from

the population without any specific criteria.
2. Stratified Sampling: Divides the population into subgroups (strata) based on certain
characteristics (e.g., age, gender). Samples are then randomly selected from each stratum
in proportion to its representation in the population.
3. Systematic Sampling: Selects every kth individual from a list or population frame
after selecting a random starting point. For example, if the population size is 1000 and
the sample size is 100, every 10th individual is selected. (In systematic sampling, the
"kth individual" refers to the specific item or individual selected in a systematic manner
from a list or population)
Here's a step-by-step explanation:
(Calculate Sampling Interval (k): The sampling interval (k) is determined by dividing
the total population size by the desired sample size. For example, if the population
size is 1000 and the desired sample size is 100, k would be 10 (1000 / 100 = 10).
Randomly Select a Starting Point: Choose a random number between 1 and k. This
number will determine the starting point for the systematic selection process.
Select Every kth Individual: Starting from the randomly chosen starting point, you
would select every kth individual or item from the list. For example, if k is 10, you
would select the 10th, 20th, 30th, and so on, until you have reached the desired
sample size.
In this context, the "kth individual" refers to the individual or item that falls on the kth
position in the ordered list. For instance, if the sampling interval is 5 (k = 5), then the
5th, 10th, 15th, and so on, individuals/items would be selected.
This method ensures a systematic and structured approach to selecting individuals
from the population, and it helps maintain the randomness and representativeness of
the sample).

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

4. Cluster Sampling:
Involves dividing the population into clusters or groups (e.g., schools, neighborhoods)
and then randomly selecting clusters to be included in the sample. All individuals within the
selected clusters are included.
Probability sampling is considered the gold standard in research because it allows for
accurate statistical inference. It ensures that the sample is representative of the population and
allows researchers to make valid generalizations based on the sample data.
However, it's important to note that probability sampling may be more complex and
time-consuming compared to non-probability sampling methods. Additionally, it may not
always be feasible or practical, especially in situations where the population is not well-
defined or accessible.

2. Non-probability sampling :

 Non-probability sampling is a method of selecting individuals or items from a population

for a research study in a way that does not guarantee every element in the population an
equal chance of being included in the sample.
 Unlike probability sampling, non-probability sampling does not rely on random selection.
 Instead, individuals are chosen based on criteria that the researcher deems relevant to the
study.

Here are some common types of non-probability sampling methods:

1.Convenience Sampling:

 Convenience sampling is a method in research where participants are selected based on

their easy accessibility and availability to the researcher.
 It's a simple and straightforward way to gather data, often chosen for its convenience, but
it may not represent the entire population accurately.
 In convenience sampling, participants are selected based on their accessibility and
convenience. This method is quick and easy, but it may not produce a representative
sample.

Example:
Imagine a researcher is conducting a study on campus attitudes towards a new
cafeteria menu. To collect data, the researcher stands near the entrance of a busy building
and approaches people as they enter or exit, asking if they would be willing to participate
in a brief survey about their cafeteria preferences.
This is an example of convenience sampling because the participants are chosen based
on their immediate availability and proximity to the researcher. Keep in mind that this
method might not capture the opinions of all students on campus, as it primarily includes
those who happened to be in the vicinity at that specific time.
SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

2.Purposive or Judgmental Sampling:

 Purposive sampling, also known as judgmental sampling, is a method in research where

participants are chosen based on specific characteristics or criteria that are relevant to the
research question.
 Unlike random sampling methods, the selection process is guided by the researcher's
judgment and expertise.
 This approach is used when researchers want to focus on a particular group or
individuals with certain attributes of interest.
 Purposive sampling involves the deliberate selection of participants based on specific
criteria relevant to the research question. This method is used when researchers want to
study individuals with certain characteristics.

3.Quota Sampling:

 Quota sampling involves setting quotas for specific subgroups (e.g., based on
demographic characteristics) to ensure representation. Researchers select participants to
meet these quotas.
 Quota sampling is a non-random method in research where specific subgroups or
categories within a population are deliberately selected to ensure they are adequately
represented in the sample.
 Researchers set predetermined quotas for each subgroup based on certain characteristics
(e.g., age, gender, ethnicity) to mirror their proportion in the population.
 Unlike random sampling, the selection process in quota sampling is based on
convenience or availability. This method is often used when obtaining a complete list of
the population is difficult, yet researchers want to maintain some degree of
representativeness across key demographic or categorical groups.

4.Snowball Sampling:
 In snowball sampling, initial participants are recruited, and then they refer additional
participants.
 It involves identifying initial participants (referred to as "seeds") and then asking them to
refer others who meet the criteria for the study. This process continues, with each new
participant potentially referring more individuals, creating a "snowball" effect.Snowball
sampling is a method in research where initial participants help identify and recruit
additional participants, forming a chain or "snowball" of referrals.
 This approach is often used to study groups or communities that are challenging to
access directly.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

Example:
Suppose a researcher is studying the experiences of individuals who have recovered from a
specific rare medical condition. Since this condition is relatively uncommon, finding
participants can be challenging. The researcher starts by identifying a few individuals who
have recovered through a support group or online forum. These individuals become the initial
participants or "seeds." The researcher then asks these initial participants to refer others they
know who have also recovered from the same condition. This process continues, with each
new participant potentially referring more individuals. The sample grows in a snowballing
fashion, allowing the researcher to gather insights from a larger group of individuals who
have experienced recovery from the condition.

 Data-Preparing, Exploring, examining, Displaying:

Data: Data" refers to factual information or observations that are collected, recorded, and
analyzed to draw conclusions, make inferences, or answer research questions. Data serves as
the foundation for research, allowing researchers to generate evidence and draw meaningful
conclusions."
i) Primary Data:
Definition: Primary data refers to information that is collected directly from original sources.
It is obtained firsthand by the researcher for a specific research purpose.
Collection Methods: Researchers gather primary data through methods like surveys,
interviews, observations, experiments, and questionnaires.
Characteristics:

 It is original and specific to the current research study.

 It is collected with a particular research objective in mind.
 Researchers have control over the collection process and can tailor it to their needs.
 It can be time-consuming and may require significant effort and resources.
Examples:

 Conducting surveys to gather information on consumer preferences for a new product.

 Conducting interviews with employees to understand workplace dynamics.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

ii)Secondary Data:
Definition: Secondary data refers to information that has already been collected by someone
else for a different purpose or research study.
Sources: Secondary data sources include published articles, reports, government publications,
books, websites, and existing datasets.
Characteristics:

 It is pre-existing and not collected for the current research study.

 It is often readily available and accessible.
 Researchers do not have control over how the data was originally collected.
 It can be a cost-effective way to access a large volume of information.

Examples:Using census data published by a government agency for demographic

analysis.Reviewing academic papers and journals to gather background information on a
specific topic.

1.Data Preparation:
Definition: Data preparation involves collecting, cleaning, organizing, and transforming raw
data into a format that is suitable for analysis.
Tasks:
Data Collection: Gathering information from various sources, which could include surveys,
observations, experiments, or existing datasets.
Data Cleaning: Identifying and correcting errors, inconsistencies, and missing values in the
dataset.
Data Entry and Coding: Entering data into a software program and assigning codes or labels
to different variables.
Data Transformation: Converting or manipulating data to create new variables or metrics.
Data Verification: Double-checking the accuracy and integrity of the dataset.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

2.Data Exploration:
Definition: Data exploration involves summarizing and examining the characteristics of the
dataset to gain a better understanding of its structure, patterns, and relationships.
Tasks:
Descriptive Statistics: Calculating measures like mean, median, mode, range, and standard
deviation to describe the central tendency and variability of the data.
Data Visualization: Creating graphs, charts, and plots to visually represent the data
distribution and relationships between variables.
Frequency Distributions: Displaying the frequency of different values or categories within a
variable.
Exploratory Data Analysis (EDA): Conducting initial analyses to identify trends, outliers, and
potential relationships between variables.

3.Data Examination:
Definition: Data examination involves conducting more advanced analyses to test hypotheses,
identify patterns, and draw meaningful conclusions from the dataset.
Tasks:
Inferential Statistics: Using statistical tests (e.g., t-tests, chi-square tests, regression analysis)
to make inferences about the population based on sample data.
Hypothesis Testing: Assessing whether observed differences or relationships in the data are
statistically significant.
Multivariate Analysis: Examining the relationships between multiple variables
simultaneously.
Correlation and Regression Analysis: Assessing the strength and direction of relationships
between variables.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET
 KARPAGA VINAYAGA
COLLEGE OF ENGINEERING AND TECHNOLOGY
(Approved by AICTE, New Delhi, Affiliated to Anna University, Chennai and Accredited by NAAC)
GST Road, Chinna kolambakkam, Madhuranthagam Taluk, Chengalpattu District – 603 308, Tamil Nadu

Department of MCA

4.Data Displaying:
Definition: Data displaying involves presenting the results of the data analysis in a clear and
understandable manner.
Tasks:
Creating Tables and Figures: Presenting key findings using tables, graphs, charts, and
diagrams.
Summarizing Results: Providing concise and interpretable summaries of the analyses
conducted.
Interpreting Findings: Explaining the implications and significance of the results in the
context of the research questions or objectives.

These steps are integral to conducting rigorous and meaningful research. Properly
preparing, exploring, examining, and displaying data ensures that researchers can draw valid
conclusions and communicate their findings effectively.

SHINY EZHILARASI.K
AP,MCA DEPT
KVCET