RESEARCH METHODOLOGY

DRM 3
 SAMPLING DESIGN
• Population
• Sample vs Census
• Sampling Frame
• Sampling Techniques
– Probability Sampling Techniques
– Non-probability Sampling Techniques
 Key Terms
• A population is the total collection of elements
about which we wish to make some inferences
• A Sample consists of some of the elements in a
population, we wish to make conclusions about the
entire population.
• A census is count of all the elements in a
population.
• Sampling frame is a list of all population elements
from which the sample will be drawn
 Why Sample
• A survey of the entire population is impracticable
• Budget and Time constraints restrict data collection
• Results from data collection are needed quickly
 Sample vs. Census
• Two conditions are appropriate for a census study:
– A census is Feasible when the population is small, and
– A census is Necessary when the elements are quite
different from each other.
• When population is small and variable, any sample
we choose may not be representative of the
population from which it is drawn.
– A census is a better choice
 Question
• Give examples of a population and a sample
• Differentiate between a population and
sampling frame
 Sampling Techniques
• The way (methods) in which we select a sample of
individuals to be research participants
• Probability Sampling:
• A sampling technique in which every member of the
population has a known, nonzero probability of being
selected
• Population size must known
• You must have a Sampling Frame
• Clear procedures to be followed when selecting a
sample
• Generalization of findings is possible
 Sampling Techniques
• Non-Probability Sampling
– respondents are chosen either on the basis of personal
judgment or convenience
– There are no systematic procedures applied in selecting
a sample
– Sampling frame is not important; but representation is
considered
– Generalization is not allowed
 Probability Sampling Techniques
• Simple random sample
• Systematic sample
• Stratified random sample
• Cluster sample or area sample
 Simple Random Sampling
• The purest form of probability sampling.
• Assures each element in the population has an
equal chance of being included in the sample
– Population size must known or estimated
– You must have a Sampling Frame
• Using either random number tables, a computer or
an online random number generator.
 Systematic Random Sampling
• Systematic sampling is a type of
probability sampling method in which sample
members from a larger population are selected
according to a random starting point and a fixed
periodic interval
• It ensures that each population element has an
equal chance of being selected
 Systematic Random sample
Determine the sampling interval N/n
– where N = population size;
– n = sample size
– e.g., N = 8000 and n = 200  N/n = 8000/200 = 40
• Determine one random number (k) in the first interval.
– e.g., k = 12
• The sample contains the kth element in each sampling
interval.
– i.e., 1st interval 12th element
– 2nd interval 12 + 40 = 52nd element
– 3rd interval 52 + 40 = 92nd element
– 4th interval  92 + 40 = 132nd element …
– 200th interval  12 + 7960 = 7072nd element
 Stratified sampling
• Stratified random sampling is a probability sampling; it
gives equal chance to all population elements
• Used when population have heterogeneous
charactristics
• Divide the population into two or more relevant and
significant strata based in a one or a number of
attributes.
• Your sampling frame is divided into a number of
subsets.
• A random sample (simple or systematic) is then drown
 Cluster Sampling
• Is similar to stratified as you need to divide the
population into discrete groups prior to sampling.
• The groups are termed clusters in this form of
sampling and can be based in any naturally
occurring grouping.
• For example, you could group your populatio by
organizations or geographical areas, countries
• The primary sampling unit is not the individual
element, but a large cluster of elements
• Clusters are normally selected using simple random
 Question
• What are Advantages and Disadvantages of
Probability Sampling Techniques
 Non-Probability Sampling
• Convenience sample
• Purposive sample
• Quota sample
• Snowball sample
 Convenience Sampling
• Convenience sampling involves selecting
conveniently those cases that are easiest to obtain
for your sample.
• The sample selection process is continued until your
required sample size has been reached.
• Although this technique of sampling is used widely,
it is prone to bias and influences that are beyond
your control, as the cases appear in the sample only
because of the ease of obtaining them.
 Purposive or Judgmental sampling
• Purposive or judgmental sampling enables you to
use your judgment to select cases that will best
enable you to answer your research question(s) and
to meet your objectives.
• This form of sample is often used when working
with very small samples such as in case research
and when you wish to select cases that are
particularly informative .
• It is recommended that you select information-rich
cases in purposive sampling with the need to be
 Quota sampling
• It is based on the premise that your sample will
represent the population as the variability in your
sample for various quota variables is the same as that
in population.
• Quota sampling is a type of stratified sample, but
selection of cases within strata is entirely non-random
• Divide population into quotas (groups having same
characteristics)
• Select respondents either conveniently or by
judgmental method
 Snowball Sampling
• Is commonly used when it is difficult to identify
members of desired population.
1. Make contact with one or two cases in the
population.
2. Ask these cases to identify further cases.
3. Ask theses new cases to identify further new cases
(and so on)
4. Stop when either no new cases are given or the
sample is as large as manageable
 Questions
• What factors should be considered in choosing
between probability and non-probability
sampling?
• Under what conditions will you use simple
random sampling over convenience sampling
in selecting a sample for your research?
• Under what conditions would a sample be
preferable to a census?
Determining a sample size
 Determining a sample size
• If you want to survey a large group of people.
– What size should your sample be?
– Twenty percent? Thirty percent?
• E.g. if you surveyed 20 % of a group of 300 you will
get samples of 60 in numbers. Which under
represent the population.
• On the other hand if your population size is 30,000,
the 20 % of that is 6000 which is too large
 Determining a Sample size
• Choice of sample size is influenced by:
• Purpose of the study
• Population size
• Allowable sampling error or level of precision
• Confidence level
• Degree of Variability in a population
 Purpose of Study
• Research Approach
– Qualitative (small) vs. Quantitative (Large)
• Research Design
– Exploratory (small)
– Descriptive (depends on your population)
– Causal (Large)
– Case study (small)
– Survey (Large)
• Resources: Financial and Time
 Population Size
• For Descriptive/Survey/Quantitative study
– If your population is small (200 people or
less, no need of sampling;
– You conduct a census and you will get 0%
sampling errors
– If your population size is large, you need to
sample
 Strategies for Determining Sample size
• Use a census for small population
– No Sampling error
• Imitate sample sizes from similar studies
– Literature review provide guidance about typical
sample sizes
• Using published tables
• Applying formulas
Calculating sample size
• Where n is the sample
size, N is the population
size, and e is the level of
precision
• NOTE: For above
approaches, the
assumption is that you
are using simple
random sampling
technique
 Other Considerations
• Data analysis techniques needed
– If descriptive statistics are to be used (e.g. mean,
frequencies; any sample will suffice, only consider
– If Multiple regression, co-variance analysis, logistic
regression analysis; you need at least 200-500 sample
size
• Number of Independent variables to be used
– A ratio of 10 observations for each independent variable
– E.g. for 10 independent variables, you need at least 100
cases or more……….
• For comparative analysis of subgroups, minimum of
 Sample size for Qualitative study
• Consider the resources available
• Use previous studies
• Consider Population size, make sure cases selected
do represent population characteristics
• Recommended 20-30 in-depth interviews are
necessary to uncover important issues
 Questions
• Joyce wants to select a sample size for her
research, but she does not have knowledge on
business research. She asks you for an advice
on what sample size she should select. Please
advise her.
DATA COLLECTION METHODS
 Types of Data
• Primary data
– Primary data refer to information obtained firsthand by
the researcher on the variables of interest for the
specific purposes of the study
– Primary are collected by the researcher
• Secondary data
– Secondary data refer to information gathered from
sources already existing
– Data has been collected by someone else apart from the
researcher
– Secondary data can be obtained
 Sources of Data
• What are possible sources of data?
• What are advantages and disadvantages of
primary data?
 Data Collection methods
• Three Major Techniques for Collecting Primary
Data
– Questionnaires
– Interviews
– Observation
 Questionnaire
• A set of questions designed to generate the data
necessary for accomplishing a research project's
objectives
• A series of written questions/items in a fixed,
rational order
 Types of Questionnaires
• Structured – for quantitative research
•
list all questions
•
put in logical sequence
•
specify precise wording to be used
•
provide pre defined categories for recording the
replies
• Main objective is that questions are standardised
• Unstructured/semi-structured – qualitative research
 Method of Administering Questionnaire

• Self administered (online, postal etc) – i.e.

completed by the respondent themselves
– Questionnaires can be delivered to the respondent by
post, e-mail attachments or publishing on a web site for
interactive completion.
• Interviewer administered (face to face)
 Before you design a questionnaire
• Constructing a Questionnaire needs a lot of time
and attention
– What kind of Information you need?
– How the information will be used?
• Make a list of what you want to know
• What do you really want to achieve? – research
objectives
• Check if information is already available somewhere
else
• Include only questions that relates to your study
(collecting too much information is expensive)
 Before you Design a Questionnaire
• Think of what you will do with each piece of
information you collect (Data Analysis)
– Frequencies and Percentages
– Rankings,
– Relationship
– Group differences
– Multivariate analysis
– Qualitative analysis
 Steps to design a questionnaire:
1. Write out your research objectives: Main and
Specific Objectives should be clear enough
2. Write out concepts/information to be collected
that relates to these objectives.
3. Review the current literature to identify already
validated questionnaires that measure your
specific area of interest.
4. Compose a draft of your questionnaire.
5. Revise the draft.
41
6. Assemble the final questionnaire.
 Questionnaire Design
• Design of the questionnaire can be split into three
elements:
• Determine the questions to be asked
• Select the question type for each question and specify
the wording
• Design the question sequence and overall questionnaire
layout
 Questionnaire Introduction
• It is important to explain to the potential
respondents why you believe they should answer
the questions
• This should be in the introduction or an
accompanying message (email) or letter (postal)
• Introductory letters, reply paid envelopes and
follow-up telephone calls also help to raise the
response rate for self-administered questionnaires
 Determine Question types
• Open vs. Closed Questions
• Single vs. multiple responses
• ‘tick one box only’ vs. “tick all boxes that apply”.
• Ranking
• E.g. Indicate by numbering from 1-4 in order where 1 is
the most important
• Scaling e.g. Likert scale
• Level of agreement with a statement
• Include N/A for those who may not have had a particular
 Question Wording
• Some general rules can be stated on question
wording:
• Be concise and unambiguous
• Ask for precise answers
• Avoid double questions
• Avoid leading questions
 Question Wording
• Be concise and unambiguous
– ‘In a month, how often do you go to shop for groceries?’
– (Ambiguous response): Never, Occasionally, Sometimes,
Often
– Unambiguous response: Never, 1 to 2 times, 3-4 times,
more than 4 times
• Do you think that the distribution of soft drinks is
adequate? (not clear enough)
– Do you think soft drinks are readily available when you
want to buy them?
 Question Wording
• Ask for precise answers
– Which Brand of Shampoo do You Use? (not precise)
– Which brand or brands of Shampoo have you
personally used at home during the last one month?
• Avoid double questions
– ‘Do you think Coca Cola is a tasty and refreshing soft
drink?’
• Avoid leading questions
– Do you agree with me that Colgate is effective in
preventing cavities?’
 Layout and Sequence
• It is good practice for the questionnaire to:
• Have a brief introductory statement
• Have a title
• Start with demographic information
• Begin with questions that will raise interest (especially for
self-completion questionnaires)
• Have numbered questions for reference purposes
• Be written in a readable font
• Make good use of italics and bold types e.g. use italics
consistently to give instructions such as ‘please tick the box’.
• Include contact and return information
 Self-Administered Questionnaire
• Respondents are more likely to commit to answer a
questionnaire when they see it is interesting, of
value, short, clearly thought through, and well
presented.
• Inducements to complete surveys can be used,
• e.g. offering respondents a report of the survey
findings or entry in a prize draw.
• ....................
 Confidentiality and Ethics
• Allow for privacy and do not ask questions which
may offend, or ask for data that is not essential.
• If not necessary, don't ask for personal details
• In surveys promises of confidentiality are often
made to the respondents to reassure and encourage
replies.
• Aside from the legal issues, it is unethical to obtain
data from respondents by misleading them about
the survey purpose and the method of analysis.
 Pilot Survey
• The aim of a pilot survey is to detect any flaws in
the questionnaire and correct these prior to the
main survey.
• The questionnaire should be tested on a small
sample first.
• If this is not possible, it should at least be tested on
some colleagues or friends.
• Having undertaken a pilot survey, amendments can
be made to the questionnaire which will help to
maximise the response rate and minimise the error
rate on answers.
 Main Survey
• Number Each Questionnaire
• Each individual questionnaire must be uniquely
identified by you, either before it is distributed or,
to preserve anonymity, afterwards.
• This identification could be via a number, or letters
and numbers.
• This code should be transferred to all the computer
records that will be produced from the
questionnaire
 Main Survey
• Deliver the Questionnaire
• Follow through on the decisions made earlier about
how the questionnaires should be administered and
who the recipients should be.
• Deadlines for distribution should have been decided
earlier with allowances for sending out reminders
or carrying out follow-up calls.
Conducting Interviews
 Interview
• Personal Interview
• Telephone interview
• Focus Groups

• Interview are conducted for Qualitative

studies
 Interview Process
• Preparation
– Interview guide
• What questions are you going to ask?
– Interview schedule
• Who you are going to interview, why, when and where?
• Conducting the Interview
• Reviewing and Describing your notes
 Preparing interview guide
• An interview guide should be created prior to all
interviews to ensure the interviews are focused and
efficient and enable comparison and summarisation
• Plan the structure of the interview.
• Prepare interview questions.
• Prepare additional notes if they assist.
• For example having an organisation chart helps in clarifying
roles and responsibilities
• The interview guide enables standardisation of interviews
for effective comparison and summarisation
 Guidelines for interview guide

• Quantifiable (for survey study)

– Open questions tend to produce long answers

that are difficult to quantify and compare

– If you need measured responses ask the

interviewee to assign a value to their answer
so direct comparisons to be made.

– E.g. How reliable is the current system, what

score would you give it out of ten?
 Preparing interview schedule
• Identify what the objectives of the interviews are,
what information you need to find out and
therefore what areas of the business you need to
obtain information from.
• Identify who needs to be interviewed to obtain this
information.
• Create an interview schedule (time), allowing time
to review and record notes between interviews.
• Book the interviews and record them in the
schedule
 Conducting the interview
• Introduction
– Always state the reason for the interview and how it will be
conducted, and how long it will take
– Introduce yourself
– Put the interviewee at ease
– Ask the interviewee if they agree to you taking notes or to be
recorded
 Conducting Interview
• Main Body
– Listen to the answers and request clarification if necessary
– Avoid making criticisms or taking sides
– Keep control of the interview: refocus the interviewee if they
are rambling or clarify if they misunderstood the question
– Stay focused and follow your interview guide
– Allow the interviewee to ask questions
• Wrap-up
– Thank the interviewee
– Tell them what are the next steps in relation to your study
– Once you have concluded your interviews, they must be
summarised to yield the ‘big picture
 Paraphrasing
• Paraphrasing is a technique used to confirm or clarify something the
interviewee has said or implied. There are three levels of
paraphrasing:
1. The first level confirms or clarifies expressed thoughts and feelings,
for example: “so there are three factors that determine the
present situation”
2. The second confirms implied thoughts or feelings, for example:
“so you would really like to change this situation”
3. The third surfaces core thoughts or feelings, for example: “you are
afraid that it might make things worse for you” or “so you think the
strategy is wrong”
(Note that with paraphrasing of feelings you can trigger a strong
emotional response particularly with this third option )
 Interview review
•Write interview notes as soon as possible after the
interview (the same day)
•Outline key findings, note emerging
themes/issues/hypotheses
•Consider how findings fit with earlier evidence
•Identify gaps to be filled in subsequent interviews
 Dos for the Interview
• Do...........
• Create rapport
• Make notes
• Be sincere
• Be objective
• Verify your findings
• Keep within the scope of the interview
• Establish the option to ask follow up questions
• Wrap up the interview and thank the interviewee
for their time.
 Don'ts of the Interview
• Do not..........
–Arrive without appointment
–Forget interviewee’s name or his/her role
–Criticise
–Interrupt
–Be impatient
–Go over time without agreement from interviewee
–Fail to thank the interviewee for their time
Conducting Focus Groups
 What is a focus group?

A focus group is a small group

discussion guided by a trained
leader, used to learn more about
opinions on a designated topic, and
then guide future action.
 When should you use a focus
group?

• When considering introducing a new program or

service
• When the main concern is depth or shading of
opinion
• When you want to ask questions that can’t easily
be asked or answered in a written survey
How to Conduct a Focus Group:
Before the meeting:
• Recheck your goals
• Consider other methods
• Find a good leader
• Find a recorder
• Decide who should be invited
• Decide about incentives
How to Conduct a Focus Group:
Before the meeting:
• Decide on the meeting particulars.
• Prepare your questions.
• Recruit your members.
• Review the arrangements.
How to Conduct a Focus Group:
When the group meets:
• Thank people for coming.
• Review the group's purpose and goals.
• Explain how the meeting will proceed and how
members can contribute.
• Set the tone by asking an opening question
and making sure all opinions on that question
are heard.
How to Conduct a Focus Group:
When the group meets:
• Ask further questions in the same general
manner.
• When all your questions have been asked, ask if
anyone has any other comments to make.
• Tell the group about any next steps that will occur
and what they can expect to happen now.
• Thank the group for coming!
How to Conduct a Focus Group:
After the meeting meets:
• Make a transcript or written summary of
the meeting.
• Examine the data for patterns, themes,
new questions, and conclusions.
• Share the results with the group.
• Use the results.
Observation Method
 Observation
• The observation method is the most commonly
used method specially in studies relating to
behavioral science.
• Observation means viewing or seeing
• observation studies are those that “involve the
systematic recording of observable phenomena or
behaviour in a natural setting”
 Why Observe
• Observation allows the researcher to study people in their
'natural setting' without their behaviour being influenced
by the presence of a researcher.
• Observational data usually consists of detailed information
about particular groups or situations.
• Observation provides a deeper, richer, understanding than
survey work which tends to produce less detailed
information about a larger number of people.
• Observation enables the research to study groups of people
together, that is, it allows for the study of interaction
between the members of a group
 Characteristics of Observation
• It is both a physical and a mental activity.
– The observation eye ‘catches’ many things which are sighted,
but attention is focused on data that are pertinent to the given
study.
• Observation is selective.
– A researcher does not observe anything and everything, but
select the range of things to be observed on the basis of the
nature, scope and objectives of his study.
• Observation is purposive and not casual.
– It is made for the specific purpose.
• It captures the natural social context in which persons’ behaviour
 Types of Observation

• Participant Observation

• Non-participant Observation

• Direct Observation

• Indirect Observation

• Controlled Observation

• Uncontrolled Observation
 Participant Observation
• In this observation, the observer is a part of the
phenomenon or group which observed and he acts
as both an observer and a participant.
• Example, a study of tribal customs by an
anthropologist by taking part in tribal activities like
folk dance.
• The people who are observed should not be aware
of the researcher’s purpose. Then only their
behaviour will be ‘natural.’
 Non-Participant Observer
• In this method, the observer stands apart and does
not participate in the phenomenon observed.
• Naturally, there is no emotional involvement on the
part of the observer.
• This method calls for skill in recording observations
in an unnoticed manner.
• Example : use of recording devices to examine the
details of how people talk and behave together.
 Direct and Indirect Observation
• Direct Observation : This means observation of an event
personally by the observer when it takes place.
• This method is flexible and allows the observer to see and
record subtle aspects of events and behaviour as they occur.
• He is also free to shift places, change the focus of the
observation.
Example: Observer is physically present to monitor
• Indirect Observation : This does not involve the physical
presence of the observer, and the recording is done by
mechanical, photographic or electronic devices.
Example : Recording customer and employee movements by a
special motion picture camera mounted in a department of
large store.
 Controlled vs. Uncontrolled
• Controlled Observation : Controlled observation is carried
out either in the laboratory or in the field.
• It is typified by clear and explicit decisions on what, how, and
when to observe.
• It is primarily used for inferring causality, and testing casual
hypothesis.
• Uncontrolled Observation : This does not involve over
extrinsic and intrinsic variables.
• It is primarily used for descriptive research.
 Planning Observation
• The use of observation method require proper planning.
• The researcher should carefully examine the relevance of
observation method to the data need of selected study.
• He must identify the specific investigative questions which
call for use of observation method. These determine the
data to be collected.
• He must decide the observation content, viz., specific
conditions, events and activities that have to be observed
for the required data.
• For each variable chosen, the operational definition should
be specified.
 Planning…..
• The observation setting, the subjects to be observed, the
timing and mode of observation, recording procedure,
recording instruments to be used, and other details of the
task should be determined.
• Observers should be selected and trained.
• The persons to be selected must have sufficient
concentration powers, strong memory power and
unobtrusive nature.
• Selected persons should be imparted both theoretical and
practical training
 Concluding remarks
• Under the observation method, the information is sought by way
of investigator‘s own direct observation without asking from the
respondent.
• For instance, in a study relating to consumer behavior, the
investigator instead of asking the brand of wrist watch used by
the respondent, may himself look at the watch.
• The main advantage of this method is that subjective bias is
eliminated, as such is relatively less demanding of active
cooperation on the part of respondents as happens to be the
case in the interview or the questionnaire method.
• This method is particularly suitable in studies (i.e. respondents)
who are not capable of giving verbal reports of their feelings for
 Home work
• Find out What are the advantages and
Disadvantages of each of the data collection
methods.