You are on page 1of 45

Business

Research Methods

Sample Designs and Sampling Procedures


Prepared By Nusrat Jahan, Faculty, IUB
Sampling Terminology
• Sample – subset of larger population
• Population or universe – any complete group that
share some set of characteristics (e.g., people, sales
territories, stores, etc.)
• Population element (sampling unit) – individual
member of population.
• Sampling frame: Listing of population from which a
sample is chosen.
• Census – investigation of all individual elements that
make up a population
• Survey – a polling / investigation of the sample
Sampling Terminology
Parameter: The variable of interest.
Statistic: The information obtained from the sample
about the parameter.
Critical assumption means the sample chosen is
representative of the population.
The Goal of Sampling is to be able to make inferences
about the population parameter from knowledge of the
relevant statistic – to draw general conclusions about the
entire body of units.
Why Sample?
• It works! Properly selected samples yield
accurate and reliable results.
– If elements are similar smaller sample is
needed
• May even be more accurate than census
– Bureau of Census uses samples to check
accuracy of the U. S. Census
• It saves resources
STAGES IN SELECTION OF A SAMPLE
2. Sampling Frame
• Sampling frame means Listing of population from
which a sample is chosen.
• It is also known as Working population
• Example: Student mailing list, Phone book, list of
customers.
• E.g. list of all the employees working in Agrabad
branch of any bank.
• Problem with lists:
Omission
Ineligible
Duplications
• Sampling frame error – occurs when population is not
accurately represented in the sampling frame.
List of Units
Census 1
2
3 4 5 3
2 6 4
1 10 7 5
11 6
12 9 8 7
13 8
14 16 17 9
15 10
11
3 4 5 12
2 6
13
1 10 7 14
11
12 9 8 15
13 16
Census 14 16 17 17
15
List of Units
Sampling Frame 1
2
3
4
3 4 5 5
2 6
6
1 10 7 7
11
12 9 8 8
13 9
14 16 17 10
15 11
12
13
Sample 14
15
16
17
Sampling Procedure: Selecting a Sample
Design
1. Non-probability Sampling
Probability of selecting any particular member is
unknown. That means, probability of selection of some
population units are zero or unknown.

Technically, inappropriate to apply statistical


techniques to project beyond the sample. That means
survey result cannot be projected to the population.

Sampling error cannot be computed.


Types of non-probability sampling:
• a) Convenience sampling
• b) Judgment sampling
• c) Quota sampling
• d) Snowball sampling
a) Convenience Sampling

• Also called haphazard or accidental


sampling
• The sampling procedure of obtaining the
people or units that are most conveniently
available
• E.g people in my class, mall intercepts,
friends, relatives.
a) Convenience Sampling
Advantages:
Very low cost and extensively used
No need for list of population

Disadvantages
Bias associated with estimates cannot be measured or
controlled
Projecting data beyond sample is inappropriate.
b) Judgment Sampling
• Also called purposive sampling
• Judgment sampling involves choosing objects /
sample that it is believed will give accurate
results
– E.g. a research is conducted on toy stores,
selecting three stores purposively from where
accurate results can be found.
b) Judgment Sampling
Advantages
Moderate cost and average use by the researcher
Useful for certain types of forecasting
Sample guaranteed to meet a specific objective

Disadvantages
Bias due to researchers’ beliefs may make sample
unrepresentative
Projecting data beyond sample is inappropriate.
c) Quota Sampling
• Quota samples are based on selecting objects until you have a
certain number (the quota) of each type.

• Still widely used (especially for telephone surveys with high non-
response levels)

• The population is divided into cells/groups on the basis of


relevant control characteristics. E.g survey population divided
into male and female.
• A quota of sample units is established for each cell / group. E.g.
from survey population comprising 100 men and 100 women, 50
men, 50 women should be chosen.

• A convenience sample is drawn for each cell until the quota is


met.
• It should not be confused with stratified sampling.
c) Quota Sampling
Advantages
Moderate cost and extensively used by the researcher
Introduces some stratification of population
Requires no list of population
Disadvantages
Introduces bias in researcher’s classification of
subjects
Non-probability selection within classes/groups means
error from population cannot be estimated
Projecting data beyond sample is inappropriate.
d) Snowball Sampling
• Initial respondents are selected by probability
methods if possible.
• Selection of additional respondents is based on
referrals from initial respondents.
• E.g. friends of friends.
• It is used sample of rare populations.
d) Snowball Sampling
Advantages
Low cost and used in special situations
It is useful in locating members of rare populations.

Disadvantages
High bias because sample unit is not independent
Projecting data beyond sample is inappropriate
2. Probability Sampling
2. Probability Sampling

• a) Simple random sample


• b) Systematic sample
• c) Stratified sample
• d) Cluster sample
• e) Multistage area sample
a) 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

For example, a school administrator of 4 schools


wishes to find out students’ opinions about food
served in the school cafeterias. He has a complete
list of all students in the schools and decides to
randomly select 150 students from the list.
In this example, each student throughout the 4
schools has an equal probability of selection to be
given the survey; therefore, it is a simple random
sample.
As the name implies, selecting a simple random
sample is, well… simple!
a) Simple Random Sampling
Here are the steps to select sample:
 Assign each member of your population a numerical
label (e.g. 1,2,3).
 Use statistical software or a random digit table to
select numerical labels /numbers at random.
Use this site: http://stattrek.com/Tables/Random.aspx
There are many other ways to obtain a simple random
sample.
 One traditional way would be the lottery method. Each of
the population members is assigned a unique number. The
numbers are placed in a bowl and thoroughly mixed. Then, a
blind-folded researcher selects the numbers. Population
members having the selected numbers are included in the
sample.
a) Simple Random Sampling
Example:
A small catering business serves 9 reception /community centers. The owner
wants to interview a sample of 4 clients in detail to find ways to improve
services to his/her clients. To avoid bias, the owner chooses a simple random
sample of size 4.
Step 1:
Each reception center is assigned a numerical label 1-9.
1 - Darlene’s Wedding Center 2 - Magic Moments Reception Hall
3 - Rustic Realm Weddings 4 - Romance Gardens
5 - Classic Weddings 6 - Old Time Chapel
7 - Lovers Lane Weddings 8 - Accents-Modern Weddings
9 - Century Falls Reception Center
Step 2:
The owner decides to use a statistical software program to generate 4
numerical labels between 1 and 9 at random. The software returns the
following numbers: 5, 8, 6, 4
Therefore, the simple random sample to be interviewed in detail will be:
Classic Weddings (5) Accents-Modern Weddings (8)
Old Time Chapel (6) Romance Gardens (4)
a) Simple Random Sampling
Advantages
Only minimum advance knowledge of population is
needed.
Easy to analyze data and compute error.
Disadvantages
Requires sampling frame
High cost
Not frequently used in practice
Respondents may be widely dispersed, hence higher
cost.
b) Systematic Sampling
• Systematic Sampling This is random sampling with a
system!

• From the sampling frame, select an initial starting point


randomly.

• and thereafter at regular intervals, like every 3rd member from


the list of populantion

• E.g. A sample of 1000 firms from a list of 200,000 firms can be


taken by drawing every 200th name from the list.
Systematic Sampling
For example, suppose you
want to sample 8 houses from
a street of 120 houses.
120/8=15, so every 15th
house is chosen after a
random starting point between
1 and 15.
If the random starting point is
11, then the houses selected
are 11, 26, 41, 56, 71, 86,
101, and 116.
Systematic Sampling
If there were 125 houses,
125/8=15.625, so should you take
every 15th house or every 16th
house? If you take every 16th
house, 8*16=128 so there is a risk
that the last house chosen does not
exist. To overcome this the random
starting point should be between 1
and 10.
On the other hand if you take every 15th house, 8*15=120 so the
last five houses will never be selected. The random starting point
should now be between 1 and 20 to ensure that every house has
some chance of being selected.
In a random sample every member of the population has an equal
chance of being chosen, which is clearly not the case here, but in
practice a systematic sample is almost always acceptable as
being random.
b) Systematic Sampling
Advantages
Moderate cost and moderately used by the
researcher.
Simple to draw sample and easy to check
Disadvantages
Periodic ordering of the population may lead to
variability or biasness.
c) Stratified Sampling

In a stratified sample the sampling frame is


divided into non-overlapping groups or stratum.

For example: on the basis of geographical areas,


age-groups, genders.

A sample is taken from each stratum, and this


sample is taken through simple random sample it
is referred to as stratified random sampling.
c) Stratified Sampling
Choice of Sample Size for each Stratum
In general the size of the sample in each stratum is
taken in proportion to the size of the stratum. This is
called proportional allocation. Suppose that in a
company there are the following staff:

and we are asked to take a sample of 40 staff, stratified


according to the above categories.
c) Stratified Sampling
The first step is to find the total number of staff (180) and
calculate the percentage in each group.
% male, full time = ( 90 / 180 ) x 100 = 0.5 x 100 = 50%
% male, part time = ( 18 / 180 ) x100 = 0.1 x 100 = 10%
% female, full time = (9 / 180 ) x 100 = 0.05 x 100 = 5%
% female, part time = (63/180)x100 = 0.35 x 100 = 35%
This tells us that of our sample of 40,
50% should be male, full time.
10% should be male, part time.
5% should be female, full time.
35% should be female, part time.
The following sample would be selected by applying simple
random sampling technique
50% of 40 is 20 (from male full time stratum)
 10% of 40 is 4 (from male part time stratum)
 5% of 40 is 2 (from female full time stratum)
 35% of 40 is 14 (from male part time stratum)
c) Stratified Sampling
Advantages
Moderately used by the researcher
Assures representation of all groups in the sample
Characteristics of each stratum can be estimated and
comparisons can be made.
Disadvantages
Requires accurate information on proportion of each
stratum in the total population
If stratified lists are not already available, they can be
costly to prepare.
d) Cluster Sampling
Cluster sampling is a sampling technique where the
entire population is divided into groups, or clusters
and a random sample of these clusters are selected.

All observations in the selected clusters are included


in the sample.
d) Cluster Sampling
d) Cluster Sampling
Advantages
Low cost and frequently used by the researcher
If clusters are geographically defined, it yields lowest
field cost
Can estimate characteristics of clusters as well as
population.
Disadvantages
Researcher must be able to assign population
members to unique cluster otherwise duplication or
omission of individual would result.
e) Multistage Sampling
In case of this sampling method, researcher performs
some combination of the first four probability sampling
techniques.
Advantages
Frequently used, especially in nationwide survey
Disadvantages
Depends on other sampling techniques
Determining Sample Size
This table is developed by Taro Yamane, in 1967 and can be used to select sample size.
The level of precision or sampling error, is often expressed in % points, (e.g., ±5%).Thus, if a
researcher finds that 60% of respondents in the sample have adopted a recommended
practice with a precision rate of ±5%, then it can be concluded that between 55% and 65% of
subjects in the population have adopted the practice.
Determining Sample Size
This table is developed by Taro Yamane, in 1967 and can be used to select sample size.
The level of precision or sampling error, is often expressed in % points, (e.g., ±5%).Thus, if a
researcher finds that 60% of respondents in the sample have adopted a recommended
practice with a precision rate of ±5%, then it can be concluded that between 55% and 65% of
subjects in the population have adopted the practice. (for more information
visithttp://edis.ifas.ufl.edu/PD006#TABLE_1)
Factors to be considered in Sample Design?
  Representativeness of sample is always important
  Degree of accuracy depends on researcher (different
considerations like cost could trade-off for a reduction in
accuracy)
  Resources constraints like (financial or human
resource) may eliminate certain methods.
  Time (if a deadline has to be followed researcher may
select less time consuming sample design)
  Advanced knowledge of the population (such as
availability of list of population member. This unavailability
may rule out some sampling method)
  National versus local project (geographic proximity of
population will influence sample design)
  Need for statistical analysis for projection beyond the
sample (non-probability method don’t allow the researcher
to utilize statistical analysis to project beyond the sample.

You might also like