Advanced Research Methods (ARM)

Company Logo

Sampling Design

Lecture - 5
 What is difference between
data and statistics?

www.themegallery.com
 Recall…

 Statistics is a tool for converting data into

information: Statistics

Data Information

But where then does data come from? How is it gathered?

How do we ensure its accurate? Is the data reliable? Is it
representative of the population from which it was drawn?

5.3
 Sampling

 Sampling is that part of statistical practice

which is concerned with the selection of
individual observations intended to yield some
knowledge about a population of concern,
especially for the purposes of statistical
inference.
 …

Sampling is the process

of selecting a small number of elements
from a larger defined target group
of elements such that
the information gathered
from the small group will allow judgments
to be made about the larger groups
 What is a sample?

A sample is a portion of the

elements of a population. A sample
is chosen to make inferences about
the population by examining or
measuring the elements in the
sample.

www.themegallery.com
 Reasons for Sampling

Researchers rarely survey the population for two

reasons(Adér, Mellenbergh, & Hand, 2008):

(1)The cost is too high and

(2)The population is dynamic, i.e., the component

of population could change over time. E.g.
patients in a hospital

www.themegallery.com Company Logo

 Advantages of sampling:

(1) The cost is lower,

(2) Data collection is faster, and
(3) It is possible to ensure homogeneity and to
improve the accuracy and quality of the data
because the data set is smaller.
Basics of Sampling Theory

Population

Element
Defined target
population
Sampling unit

Sampling frame
 Selection of Elements

 Population

 Population Element

 Sampling

 Survey

 Census
 Definitions
 Population: The target population is the collection of
elements or objects that possess the information sought
by the researcher and about which inferences are to be
made. The target population should be defined in terms
of elements, sampling units, extent, and time.
 An element is the object about which or from which

the information is desired, e.g., the respondent.

 A sampling unit is an element, or a unit containing

the element, that is available for selection at some

stage of the sampling process. E.g. organization
 Extent refers to the geographical boundaries.

 Time is the time period under consideration.

 Sampling frame

 Sampling frame (synonyms: "sample frame",

"survey frame") is the actual set of units from
which a sample has been drawn: in the case of a
simple random sample, all units from the
sampling frame have an equal chance to be
drawn and to occur in the sample.
 In the ideal case, the sampling frame should
coincide with the population of interest.

www.themegallery.com Company Logo

 Example
 Consider, a survey aimed at establishing the number of potential
customers for Easypaisa in the population of Islamabad City.
The research team has drawn 1000 numbers at random from a
telephone directory for the city, made 200 calls each day from
Monday to Friday from 8am to 5pm and asked some questions.
 In this example, population of interest is all inhabitants of the city; the
sampling frame includes only those dwellers who satisfy all the following
conditions:
 has a telephone;

 the telephone number is included in the directory;

 likely to be at home from 8am to 5pm from Monday to Friday;

 not a person who refuses to answer all telephone surveys.

 Sampling Plans…

 A sampling plan is just a method or procedure

for specifying how a sample will be taken from a
population.

5.14
 What is a Good Sample?

 Accurate: absence of bias

 Precise estimate: sampling error

 Is sample unbiased?

www.themegallery.com Company Logo

 Types of Errors

 Sampling and
 Non-Sampling Errors…

www.themegallery.com Company Logo

 Sampling Error

 Sampling error is any type of bias that is

attributable to mistakes in either drawing a sample or
determining the sample size

 Sampling errors are caused by sampling design. It

includes:
(1) Selection error: Incorrect selection probabilities
are used.
(2) Estimation error: Biased parameter estimate
because of the elements in these samples.
  E.g. Two samples of size 10 of 1,000 households. If
we happened to get the highest income level data
points in our first sample and all the lowest income
levels in the second, this delta is due to sampling
error.

 Increasing the sample size will reduce this type of

error.

www.themegallery.com Company Logo

 Non-sampling errors
 Nonsampling errors are more serious and are due to mistakes
made in the acquisition of data or due to the sample observations
being selected improperly. Non-sampling errors are caused by the
mistakes in data processing. It includes:
(1) Overcoverage: Inclusion of data from outside of the
population.
(2) Undercoverage: Sampling frame does not include elements in
the population.
(3) Measurement error: The respondent misunderstand the
question.
(4) Processing error: Mistakes in data coding.
(5) Non-response:

www.themegallery.com Company Logo

 Increasing the sample size will not reduce this type of error.
 Acquisition errors arise from the recording of incorrect
responses, due to:
 — incorrect measurements being taken because of faulty equipment,
 — mistakes made during transcription from primary sources,
 — inaccurate recording of data due to misinterpretation of terms, or
 — inaccurate responses to questions concerning sensitive issues.
 Sampling Methods

Probability Nonprobability
sampling sampling
 Steps in Sampling Design

 What is the relevant population?

 What are the parameters of interest?
 What is the sampling frame?
 What is the type of sample?
 What size sample is needed?
 How much will it cost?
 Steps

Define the Population

Determine the Sampling Frame

Select Sampling Technique(s)

Determine the Sample Size

Execute the Sampling Process

 Classification of Sampling
Techniques

Sampling Techniques

Nonprobability Probability
Sampling Techniques Sampling Techniques

Convenience Judgmental Quota Snowball

Sampling Sampling Sampling Sampling

Simple Random Systematic Stratified Cluster Other Sampling

Sampling Sampling Sampling Sampling Techniques
Company Logo

Non-Probability
Sampling Designs

www.themegallery.com Company Logo

Nonprobability Sampling Methods

Convenience sampling relies

upon convenience and access
Judgment sampling relies upon belief
that participants fit characteristics
Quota sampling emphasizes representation
of specific characteristics
Snowball sampling relies upon respondent
referrals of others with like characteristics
 Nonprobability Sampling

Reasons to use
 Procedure satisfactorily meets the sampling
objectives
 Lower Cost
 Limited Time
 Not as much human error as selecting a
completely random sample
 Total list population not available
 Nonprobability Sampling

 Convenience Sampling
 Purposive Sampling
 Judgment Sampling
 Quota Sampling
 Snowball Sampling
 Convenience Sampling

Convenience sampling attempts to obtain a sample of

convenient elements. Often, respondents are selected
because they happen to be in the right place at the right
time.

 use of students, and members of social organizations

 mall intercept interviews without qualifying the
respondents
 department stores using charge account lists
 “people on the street” interviews
 Judgmental Sampling

Judgmental sampling is a form of convenience

sampling in which the population elements are selected
based on the judgment of the researcher.

 test markets
 purchase engineers selected in industrial marketing
research
 expert witnesses used in court
 Quota Sampling

Quota sampling may be viewed as two-stage restricted judgmental

sampling.
 The first stage consists of developing control categories, or quotas, of

population elements.
 In the second stage, sample elements are selected based on

convenience or judgment.

Population Sample
composition composition
Control
Characteristic Percentage Percentage Number
Sex
Male 48 48 480
Female 52 52 520
____ ____ ____
100 100 1000
 Snowball Sampling

In snowball sampling, an initial group of respondents

is selected, usually at random.

 After being interviewed, these respondents are asked

to identify others who belong to the target population
of interest.
 Subsequent respondents are selected based on the
referrals.
Company Logo

Probability Sampling
Designs

www.themegallery.com Company Logo

 Probability Sampling Designs

 Simple random sampling

 Systematic sampling
 Stratified sampling
 Proportionate
 Disproportionate
 Cluster sampling
 Double sampling
 Simple Random Sampling

 Each element in the population has a known and equal

probability of selection.
 Each possible sample of a given size (n) has a known and
equal probability of being the sample actually selected.
 This implies that every element is selected independently
of every other element.
 Systematic Sampling
 The sample is chosen by selecting a random starting point and
then picking every ith element in succession from the sampling
frame.
 The sampling interval, i, is determined by dividing the population
size N by the sample size n and rounding to the nearest integer.
 When the ordering of the elements is related to the characteristic
of interest, systematic sampling increases the representativeness
of the sample.
 For example, there are 100,000 elements in the population and a
sample of 1,000 is desired. In this case the sampling interval, i, is
100. A random number between 1 and 100 is selected. If, for
example, this number is 23, the sample consists of elements 23,
123, 223, 323, 423, 523, and so on.
 Stratified Sampling

 A two-step process in which the population is partitioned

into subpopulations, or strata.
 The strata should be mutually exclusive and collectively
exhaustive in that every population element should be
assigned to one and only one stratum and no population
elements should be omitted.
 Next, elements are selected from each stratum by a
random procedure, usually SRS.
 A major objective of stratified sampling is to increase
precision without increasing cost.
 Stratified Sampling
 The elements within a stratum should be as homogeneous as
possible, but the elements in different strata should be as
heterogeneous as possible.
 Finally, the variables should decrease the cost of the stratification
process by being easy to measure and apply.
 In proportionate stratified sampling, the size of the sample drawn
from each stratum is proportionate to the relative size of that
stratum in the total population.
 In disproportionate stratified sampling, the size of the sample from
each stratum is proportionate to the relative size of that stratum and
to the standard deviation of the distribution of the characteristic of
interest among all the elements in that stratum.
 Cluster Sampling
 The target population is first divided into mutually exclusive and
collectively exhaustive subpopulations, or clusters.
 Then a random sample of clusters is selected, based on a probability
sampling technique such as SRS.
 For each selected cluster, either all the elements are included in the sample
(one-stage) or a sample of elements is drawn probabilistically (two-stage).
 Elements within a cluster should be as heterogeneous as possible, but
clusters themselves should be as homogeneous as possible. Ideally, each
cluster should be a small-scale representation of the population.
 In probability proportionate to size sampling, the clusters are
sampled with probability proportional to size. In the second stage, the
probability of selecting a sampling unit in a selected cluster varies inversely
with the size of the cluster.
 Types of Cluster Sampling
Fig. 11.3 Cluster Sampling

One-Stage Two-Stage Multistage

Sampling Sampling Sampling

Simple Cluster Probability

Sampling Proportionate
to Size Sampling
 Sample vs. Census

Type of Study

1. Budget
 Sample Sizes Used in Marketing
Research Studies
Table 11.2

Type of Study

Problem identificati
Factors to Consider in Sample Design

Research objectives Degree of accuracy

Resources Time frame

Knowledge of
target population Research scope

Statistical analysis needs

 Determining Sample Size

 How many completed questionnaires do we need

to have a representative sample?
 Generally the larger the better, but that takes
more time and money.
 Answer depends on:
 How different or dispersed the population is.
 Desired level of confidence.
 Desired degree of accuracy.
 Common Methods for Determining
Sample Size

 Common Methods:
 Budget/time available
 Executive decision
 Statistical methods
 Historical data/guidelines
 Factors Affecting Sample Size for Probability
Designs

 Variability of the population characteristic

under investigation
 Level of confidence desired in the estimate
 Degree of precision desired in estimating the
population characteristic
 n = [N2Z2]/[Ne2 + σ2Z2]
Where
 e is the specified error
 σ is the SD of the population
 N is the population
 Z is the table value of Z-Table. For a 95%
Confidence Interval, value of Z is 1.96

www.themegallery.com Company Logo

Probability Sampling and
Sample Sizes

For a simple sample size calculator, click here:

http://www.surveysystem.com/sscalc.htm
Company Logo

Research Design

www.themegallery.com Company Logo

 Measurement

 Selecting observable empirical events

 Using numbers or symbols to represent aspects

of the events

 Applying a mapping rule to connect the

observation to the symbol
 What is Measured?

 Objects:
 Things of ordinary experience
 Some things not concrete
 Properties: characteristics of objects
 Characteristics of Data

 Classification
 Order
 Distance (interval between numbers)
 Origin of number series
 Data Types

Order Interval Origin

Nominal none none none

Ordinal yes unequal none

Interval yes equal or none

unequal
Ratio yes equal zero
 Sources of Measurement
Differences
 Respondent
 Situational factors
 Measurer or researcher
 Data collection instrument
 Validity

 Content Validity

 Criterion-Related Validity
 Predictive
 Concurrent

 Construct Validity
 Reliability

 Stability
 Test-retest
Equivalence
 Parallel forms
 Internal Consistency
 Split-half
 KR20
 Cronbach’s alpha
 Practicality

 Economy

 Convenience

 Interpretability
Company Logo

MEASUREMENT
SCALES

www.themegallery.com Company Logo

 What is Scaling?

 Scaling is assigning numbers to indicants of the

properties of objects
 Types of Response Scales

 Rating Scales
 Ranking Scales
 Categorization
 Types of Rating Scales
 Simple category • Numerical
 Multiple choice,
• Multiple rating
single response
 Multiple choice,
• Fixed sum
multiple response • Stapel
 Likert scale • Graphic rating
 Semantic differential
 Rating Scale Errors to Avoid

 Leniency
 Negative Leniency
 Positive Leniency
 Central Tendency
 Halo Effect
 Types of Ranking Scales

 Paired-comparison

 Forced Ranking

 Comparative
 Dimensions of a Scale

 Unidimensional

 Multidimensional
 Scale Design Techniques

 Arbitrary scaling
 Consensus scaling
 Item Analysis scaling
 Cumulative scaling
 Factor scaling
  Sarndal, Swenson, and Wretman (1992), Model
Assisted Survey Sampling, Springer-Verlag
 Fritz Scheuren (2005). "What is a Margin of
Error?", Chapter 10, in "What is a Survey?",
American Statistical Association, Washington

www.themegallery.com Company Logo

Company Logo

Thank you for your

kind attention
Go forth and research….
….but be careful out there.