Research Methodology

Sample Designs and Sampling

Procedures
 Sampling Terminology
• Sample
• Population or universe
• Population element
• Census
 Sample
• Subset of a larger population
 Population
• A population is the total collection of elements
about which we wish to make some inferences.

• Any complete group

– People
– Sales territories
– Stores
 Census
• Investigation of all individual elements that
make up a population

A census is a count of
all the elements in a
population.
 Population Frame
• A list, map, directory, or other source used to
represent the population
• Overregistration -- the frame contains all members of
the target population and some additional elements
Example: using the chamber of commerce
membership directory as the frame for a target
population of member businesses owned by women.
• Underregistration -- the frame does not contain all
members of the target population.
Example: using the chamber of commerce
membership directory as the frame for a target
population of all businesses.
 Reasons for Taking a Census

• Eliminate the possibility that a random

sample is not representative of the
population.

• The person authorizing the study is

uncomfortable with sample information.
 Sampling
• The process of using a small number of
items or parts of larger population to make a
conclusions about the whole population
 Reasons for Sampling
• Sampling can save money.
• Sampling can save time.
• For given resources, sampling can broaden
the scope of the data set.
• Because the research process is sometimes
destructive, the sample can save product.
• If accessing the population is impossible;
sampling is the only option.
© 2002 Thomson / Slide 7-9
South-Western
 Selecting samples
Population, sample and individual cases

Source: Saunders et al. (2009)

Figure 7.1 Population, sample and individual cases

 The need to sample

Sampling- a valid alternative to a census when

• A survey of the entire population is impracticable

• Budget constraints restrict data collection

• Time constraints restrict data collection

• Results from data collection are needed quickly

 Overview of sampling techniques
Sampling techniques

Source: Saunders et al. (2009)

Figure 7.2 Sampling techniques
Stages in the
Define the target population
Selection
of a Sample Select a sampling frame

Determine if a probability or nonprobability

sampling method will be chosen

Plan procedure
for selecting sampling units

Determine sample size

Select actual sampling units

Conduct fieldwork
 Target Population
• The specific , complete group to research
project
 Sampling Frame
• A sample frame is the listing of all population
elements from which the sample will be drawn.
 Sampling Units
• Group selected for the sample
• Primary Sampling Units (PSU)
• Secondary Sampling Units
• Tertiary Sampling Units
 Random vs Nonrandom
Sampling
• Random sampling
• Every unit of the population has the same probability of
being included in the sample.
• A chance mechanism is used in the selection process.
• Eliminates bias in the selection process
• Also known as probability sampling
• Nonrandom Sampling
• Every unit of the population does not have the same
probability of being included in the sample.
• Open the selection bias
• Not appropriate data collection methods for most
statistical methods
• Also known as nonprobability sampling
 Random Sampling Error
• The difference between the sample results
and the result of a census conducted using
identical procedures
• Statistical fluctuation due to chance
variations
 Systematic Errors
• Nonsampling errors
• Unrepresentative sample results
• Not due to chance
• Due to study design or imperfections in
execution
 Bias
• Bias is a systematic error that can prejudice
your evaluation findings in some way.
• Sampling bias is consistent error that arises
due to the sample selection.
• For survey researchers, sampling biases for
averages derive from three sources: (1)
imperfect sampling frames, (2) nonresponse
bias, and (3) measurement error.
• For example, distributing a questionnaire at
the end of a 3-day conference is likely to
include more people who are committed to the
conference so their views would be
overrepresented.
Errors Associated with Sampling
• Sampling frame error
• Random sampling error
• Nonresponse error
 Two Major Categories of
Sampling
• Probability sampling
• Known, nonzero probability for every
element
• Nonprobability sampling
• Probability of selecting any particular
member is unknown
 Sampling
Non Probability Samples
A non probability sample relies on the researcher
selecting the respondents.
They are considered to be:
• Interpretive
• Subjective
• Not scientific
• Qualitative
• Unrepresentative
 Nonprobability Sampling
• Convenience
• Judgment
• Quota
• Snowball
 Sampling
Probability Samples
Probability samples offer each respondent an
equal probability or chance at being included in
the sample.
They are considered to be:
• Objective
• Empirical
• Scientific
• Quantitative
• Representative
 Probability Sampling
• Simple random sample
• Systematic sample
• Stratified sample
• Cluster sample
• Multistage area sample
 Convenience Sampling

• Convenience samples are nonprobability

samples where the element selection is
based on ease of accessibility. They are the
least reliable but cheapest and easiest to
conduct.
• Examples include informal pools of friends
and neighbors, people responding to an
advertised invitation, and “on the street”
interviews.
 Judgment Sampling
• Also called purposive sampling
• An experienced individual selects the
sample based on his or her judgment about
some appropriate characteristics required of
the sample member
 Quota Sampling
• Ensures that the various subgroups in a
population are represented on pertinent
sample characteristics
• To the exact extent that the investigators
desire
• It should not be confused with stratified
sampling.
 Snowball Sampling
• A variety of procedures
• Initial respondents are selected by
probability methods
• Additional respondents are obtained from
information provided by the initial
respondents
 Simple Random Sampling
• A sampling procedure that ensures that each
element in the population will have an equal
chance of being included in the sample
 Simple Random Sampling:
Random Number Table
9 9 4 3 7 8 7 9 6 1 4 5 7 3 7 3 7 5 5 2 9 7 9 6 9 3 9 0 9 4 3 4 4 7 5 3 1 6 1 8
5 0 6 5 6 0 0 1 2 7 6 8 3 6 7 6 6 8 8 2 0 8 1 5 6 8 0 0 1 6 7 8 2 2 4 5 8 3 2 6
8 0 8 8 0 6 3 1 7 1 4 2 8 7 7 6 6 8 3 5 6 0 5 1 5 7 0 2 9 6 5 0 0 2 6 4 5 5 8 7
8 6 4 2 0 4 0 8 5 3 5 3 7 9 8 8 9 4 5 4 6 8 1 3 0 9 1 2 5 3 8 8 1 0 4 7 4 3 1 9
6 0 0 9 7 8 6 4 3 6 0 1 8 6 9 4 7 7 5 8 8 9 5 3 5 9 9 4 0 0 4 8 2 6 8 3 0 6 0 6
5 2 5 8 7 7 1 9 6 5 8 5 4 5 3 4 6 8 3 4 0 0 9 9 1 9 9 7 2 9 7 6 9 4 8 1 5 9 4 1
8 9 1 5 5 9 0 5 5 3 9 0 6 8 9 4 8 6 3 7 0 7 9 5 5 4 7 0 6 2 7 1 1 8 2 6 4 4 9 3

• N = 30
• n=6
 Simple Random

Advantages Disadvantages
• Easy to implement with • Requires list of
random dialing population elements
• Time consuming
• Larger sample needed
• Produces larger errors
• High cost

14-33
 Systematic Sampling
• A simple process
• Every nth name from the list will be drawn
 Systematic Sampling
• Convenient and relatively easy
N
to administer k = ,
n
• Population elements are an
where:
ordered sequence (at least,
n = sample size
conceptually).
• The first sample element is N = population size

selected randomly from the k = size of selection interval

first k population elements.
• Thereafter, sample elements
are selected at a constant
interval, k, from the ordered
sequence frame.
 Systematic

Advantages Disadvantages
• Simple to design • Periodicity within
• Easier than simple population may skew
random sample and results
• Easy to determine • Trends in list may bias
sampling distribution of results
mean or proportion • Moderate cost

14-36
Stratified Sampling

• Probability sample
• Subsamples are drawn
within different strata
• Each stratum is more
or less equal on some
characteristic
• Do not confuse with
quota sample
 Stratified Random Sample: Population
of FM Radio Listeners

Stratified by Age

20 - 30 years old
(homogeneous within)
(alike) Hetergeneous
(different)
30 - 40 years old between
(homogeneous within)
(alike) Hetergeneous
(different)
40 - 50 years old between
(homogeneous within)
(alike)
 Stratified

Advantages Disadvantages
• Control of sample size in • Increased error if subgroups
strata are selected at different rates
• Increased statistical • Especially expensive if strata
efficiency on population must be
• Provides data to represent created
and analyze subgroups • High cost
• Enables use of different
methods in strata

14-39
 Cluster Sampling
• Population is divided in to into
nonoverlapping clusters or areas

• Each cluster is a miniature, or

microcosm, of the population.

• A subset of the clusters is selected

randomly for the sample.
 Cluster Sampling
u Advantages
• More convenient for geographically dispersed
populations
• Reduced travel costs to contact sample elements
• Simplified administration of the survey
• Unavailability of sampling frame prohibits using other
random sampling methods
u Disadvantages
• Statistically less efficient when the cluster elements
are similar
• Costs and problems of statistical analysis are greater
than for simple random sampling
 Cluster Sampling:
Some Test Market Cities
• Grand Forks
• Fargo • Portland

•Boise •Buffalo• Pittsfield

• Milwaukee
• Cedar
Rapids
• Denver •Cincinnati
•San Jose • Kansas •Louisville
City

•San •Phoenix •Atlanta

Diego •Tucson •Sherman-
•Odessa- Dension
Midland
 Cluster

Advantages Disadvantages
• Provides an unbiased • Often lower statistical
estimate of population efficiency due to subgroups
parameters if properly done being homogeneous rather
• Economically more efficient than heterogeneous
than simple random • Moderate cost
• Lowest cost per sample
• Easy to do without list

14-43
 What is the
Appropriate Sample Design?
• Degree of accuracy
• Resources
• Time
• Advanced knowledge of the population
• National versus local
• Need for statistical analysis
 Internet Sampling is Unique
• Internet surveys allow researchers to rapidly
reach a large sample.
• Speed is both an advantage and a
disadvantage.
• Sample size requirements can be met
overnight or almost instantaneously.
• Survey should be kept open long enough so
all sample units can participate.
 Internet Sampling
• Major disadvantage
– lack of computer ownership and Internet
access among certain segments of the
population
• Yet Internet samples may be representative
of a target populations.
– target population - visitors to a particular Web
site.
• Hard to reach subjects may participate
 Web Site Visitors
• Unrestricted samples are clearly
convenience samples
• Randomly selecting visitors
• Questionnaire request randomly "pops up"
• Over- representing the more frequent
visitors
 Internet Samples
• Recruited Ad Hoc Samples
• Opt-in Lists
 4. Ratio Scale
Ratio scales are quantitative measures with fixed or true
zero.
Ratio scales has all four properties of scales that are
described above.
For example, a weighing scale is a ratio scale. Some other
examples are height, price, sales, revenue, profit etc. In all
these cases zero implies absence of that characteristic.
 Strengths Of Multiple-Item
Scales
• Validity
• Content validity
• Construct validity
• Predictive validity
• Reliability
• Test-retest reliability
• Split-half reliability
• Sensitivity
Copyright © Houghton 9 | 50
Mifflin Company. All
 Validity
• The validity of a scale is the extent to which
it is a true reflection of the underlying
variable it is attempting to measure

9 | 51
 VALIDITY

• Content”: related to objectives and their

sampling.
• “Construct”: referring to the theory underlying
the target.
• “Criterion”: related to concrete criteria in the
real world. It can be concurrent or predictive.
• “Concurrent”: correlating high with another
measure already validated.
• “Predictive”: Capable of anticipating some later
measure.
• “Face”: related to the test overall appearance.
 Content Validity
• Face validity or content validity is the
extent to which the content of a
measurement scale seems to tap all relevant
facets of an issue that can influence
respondents’ attitudes

9 | 53
Exhibit 9.5 Types of Equivalence

Copyright © Houghton 9 | 54
Mifflin Company. All
 Construct Validity
• Construct Validity is the nature of the
underlying variable or construct measured
by the scale

9 | 55
 Predictive Validity
• Predictive Validity refers to how well the
attitude measure provided by the scale
predicts some other variable or
characteristic

9 | 56
 Reliability
• Reliability measures how consistent or
stable the ratings generated by the scale are
likely to be

9 | 57
 Test-Retest Reliability
• Test-Retest Reliability measures the
stability of ratings over time and involves
administering the scale to the same group of
respondents at two different times

9 | 58
 Split-Half Reliability
• Split-Half Reliability measures the degree
of consistency across items within a scale
and can only be assessed for multiple-item
scales

9 | 59
 Sensitivity
• Sensitivity focuses specifically on its
ability to detect subtle differences in the
attitudes being measured

9 | 60
 Attitudes
• Attitudes are similar to beliefs, except that
they also involve respondents’ evaluative
judgments
• For instance, do respondents feel print
advertisements for cigarettes should be
banned?

9 | 61
 Attitudes –
Conceptually and Operationally
• A conceptual definition of attitude may be “a
predisposition to respond favorably or unfavorably to a
stimulus object”
• An operational definition of attitude refers to a person’s
attitude towards a particular retail store that may be
measured as the total of the person’s expressed degree of
agreement, on a 5-point, “strongly agree” to “strongly
disagree” scale, with each of a set of 20 evaluative
statements about various aspects of the retail store

9 | 62
 Attitude Scaling
• Attitudes
– Widely believed to be a key determinant of behavior
– Can only be inferred and cannot be directly ascertained
• Measures in which inferences are drawn from
– Observed overt behavior
– Individual's reaction
– Performance on objective tasks
– Physiological reactions

9 | 63
 Observing Overt Behavior
• Observation of overt behavior is useful
when other attitude measurement methods
are inconvenient or infeasible
• An observation study can be used to
ascertain the attitudes of very young
children toward a variety of toys

Copyright © Houghton 9 | 64
Mifflin Company. All
Analyzing Reactions to Partially
Structured Stimuli
• Projective Techniques
– The approach of analyzing reactions to partially
structured stimuli involves asking respondents
to react to or describe in some fashion, an
incomplete, vague stimulus

9 | 65
 Evaluating Performance on
Objective Tasks
• To evaluate performance on objective tasks,
respondents are asked to complete an
ostensibly objective, well-defined task
• The nature of their performance is then
analyzed to infer their attitudes

9 | 66
 Monitoring Physiological
Responses
• Monitoring physiological responses is based
on the premise that a person's emotional
reactions to a stimulus will be accompanied
by corresponding involuntary physiological
changes

9 | 67
 Self-report Measurements of
Attitudes
• This method involves asking respondents
relatively direct questions concerning
attitudes toward whatever is of interest to
the researcher
• The questions are typically in the form of
rating scales on which respondents check
off appropriate positions that best reflect
their feelings
9 | 68
 Graphic Formats
• A graphic rating scale presents a continuum,
in the form of a straight line, along which a
theoretically infinite number of ratings are
possible
• Example: Indicate your overall opinion
about eBay by placing a  mark at an
Very Very
Bad Good
• appropriate position on the line below.
9 | 69
 Itemized Formats
• Itemized rating scales have a set of distinct
response categories
• Any suggestion of an attitude continuum
underlying the categories is implicit
• They essentially take the form of the
multiple-category questions

9 | 70
 Forced Response Choices
• A forced-choice scale does not give
respondents the option of expressing a
neutral or middle-ground attitude

9 | 71
Forced Response Choices (Cont’d)
Indicate your overall opinion about effectiveness of HR by
checking one of the following categories:

Very Neither Bad Very

Bad Bad nor Good Good Good
[ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ]
1 2 3 4 5 6 7 8 9

What is your overall rating of HR in comparison with previous

organisation you worked?

Much worse Worse About the same Better Much better

( ) ( ) ( ) ( ) ( )

9 | 72
 Non-forced Response Choices
• A non-forced-choice scale give respondents
the option to express a neutral attitude

9 | 73
Non-forced Response Choices
(Cont’d)
Indicate your overall opinion about effectiveness of HR by placing
a  mark in the category that best summarizes your feelings.

Very Very
Bad Good
[ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ] [ ]
1 2 3 4 5 6 7 8 9

What is your overall rating of HR in comparison with previous

organisation you worked?

Much worse Worse Better Much better

( ) ( ) ( ) ( )
9 | 74
Unbalanced Response Choices
• An unbalanced rating scale that can be used
if respondents’ opinions about a subject are
anticipated to be predominantly positive

9 | 75
Labeled Response Choices

9 | 76
Unlabeled Response Choices

9 | 77
Exhibit 9.2 Rating Scales with
Picture Labels

9 | 78
 Number of Scale Positions
• A scale with a large number of positions
will not be meaningful if respondents are
unable to make fine mental distinctions with
respect to whatever is being measured
• More precise measurements should result
as the number of scale positions increase

9 | 79
 Commonly Used Multiple-item
Scales
• Likert Scale
• Semantic-Differential Scale

9 | 80
• In 1932, Renis Likert invented a measurement
method, called the Likert Scales (often called
a rating scale), used in questionnaires such as
attitude surveys. They allow answers that range
from such choices “strongly disagree” to “strongly
agree.” It is the most widely used scale in survey
research. When responding to a Likert
questionnaire item, respondents specify their level
of agreement to a statement.
9 | 81
• for example:

• 1 2 3 4 5 6 7 Strongly ,agree ,Slightly

Agree,Undecided ,Slightly Agree, Strongly
Disagree ,Disagree, Agree
• 1. My job provides a lot of variety. _____
• 2. My job provides the opportunity for
independent action. _____
9 | 82
 Table 9.2 Likert Scale Items
Strongly Disagree Neither Agree Strongly
Disagree Agree nor Agree
Disagree
1. The online auction site
contains an abundance of exhibits ________ ________ ________ ________ ________

2. User registration
is complex at this site ________ ________ ________ ________ ________

3. The auction site commission

is reasonable ________ ________ ________ ________ ________
4. The auction site responds
to complaints quickly ________ ________ ________ ________ ________
5. The auction site is not
careful with personal information ________ ________ ________ ________ ________
6. The auction site support
system is confusing ________ ________ ________ ________ ________

9 | 83
 Semantic-Differential
Scale
The Semantic Differential (SD)
measures people's reactions to stimulus
words and concepts in terms of ratings
on bipolar scales defined with
contrasting adjectives at each end.

9 | 84
Exhibit 9.3 Semantic-Differential
Scale Items

9 | 85
 Exhibit 9.4 Pictorial Profiles
Based on Semantic-Differential
Ratings

9 | 86