Selecting Samples

11/15/24 Ali Yassin Sheikh, PhD 1

 Selecting Sample Size

• Introduction
• Probability and Non-probability sampling
techniques
– Selecting and justifying appropriate sampling
techniques
– Assessing the representativeness of respondents
– Generalizing from a sample
• Conclusion

11/15/24 Ali Yassin Sheikh, PhD 2

 Selecting samples
Population, sample and individual cases

Source: Saunders et al. (2009)

Figure
11/15/24 7.1 Population, sampleAliand individual
Yassin cases
Sheikh, PhD 3
 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

11/15/24 Ali Yassin Sheikh, PhD 4

 Introduction, cont…
• An overview of sampling techniques:
– Probability or representative sampling:
• Selection method in which the chance, or
probability, of each case being selected from the
population is known and is not zero.
– Simple random, systematic, stratified random, cluster,
and multi-stage
– Non-probability or judgemental sampling:
• Quota, snowball, convenience, purposive and self-
selection

11/15/24 Ali Yassin Sheikh, PhD 5

 Probability Sampling
• It is most commonly associated with:
– Survey-based research strategies
– where you need to make conclusion from your sample
to answer your research questions.
• It has four stages of process:
– Identify a suitable sampling frame based on your
research questions
– Decide on a suitable sample size
– Select the most appropriate sampling technique and
select the sample
– Check that the sample is representative of the
population

11/15/24 Ali Yassin Sheikh, PhD 6

 Probability Sampling, cont…
• Stage one: identifying sample frame/target
population and generalizability issues
– Sampling frame is a complete list of all the
cases in the population from which your
sample will be drawn.
– Make sure your sample frame is complete,
accurate and up to date
– It should be valid and reliable
– You should not generalize beyond your
sampling frame
11/15/24 Ali Yassin Sheikh, PhD 7
Example 1: Sample frame/ Target
population
• The target population of this study was finance
employees of remittance companies in
Mogadishu because we are more dependent on
remittances and they are a good source of
information to analyze the topic. There are at
least 23 remittance companies operating inside
Mogadishu (Abdirizak,2013).

11/15/24 Ali Yassin Sheikh, PhD 8

 Example 2
• Target population:
• The target population of this study are
students at SIMAD university, the sample
frame contains number of students of all
faculties which are 3296 (secretary, 2014).

11/15/24 Ali Yassin Sheikh, PhD 9

 Probability Sampling, cont..
• Stage two: Deciding on a suitable sample size
– The larger your sample size the lower the likely error
in generalizing to the population.
– Consider the confidence you need to have in your
data
– Think about the types of analysis you are going to
undertake
– Set the size of the total population from which your
sample is being drawn
– Finally develop your sample size through judgement
or calculation or based on the literature

11/15/24 Ali Yassin Sheikh, PhD 10

 Sample size calculators
• Slovin’s Formula
• Slovins’s formula is used to calculate an
appropriate sample size from a population.
n = N / (1 + Ne2) where n = Number of
samples, N = Total population and e =
Error tolerance.

11/15/24 Ali Yassin Sheikh, PhD 11

• According to Israel (1992), there are several techniques
for determining the actual sample size. However, this
study follows the formula technique, which calculates the
desired sample size. Yamani (1967, cited in Israel, 1992)
provided a useful formula(Slovin’s Formula) to calculate
the sample size, considering the level of error tolerated.

11/15/24 Ali Yassin Sheikh, PhD 12

 Sample size-from literature
• The target population of this study was the
women entrepreneurs who sell garments
groceries, jewelry and petroleum products in
Mogadishu, since there are no comprehensive
directory of women entrepreneurs in Somalia,
the researcher team took 200 women
entrepreneurs as a target population for this
study. This sample size is suitable because
previous studies was used such as (Ali,2013).

11/15/24 Ali Yassin Sheikh, PhD 13

 Probability Sampling, cont…
• Stage two cont…
– Stutely (2003) advice of a minimum number of 30 for
statistical analysis provides a useful rule of thumb for
the smallest number in each category within your
overall sample.
– You should attempt to increase your response rate.
– Your minimum sample size is affected the required
response rate to arrive the actual sample size.
– A response rate of 35% is considered as reasonable
(Baruch, 1999).

11/15/24 Ali Yassin Sheikh, PhD 14

 Probability Sampling, cont…
• Stage three: Selecting the most
appropriate sampling technique and the
sample
– Simple random: involves selecting the sample
at random from the sampling frame using
either random number table or a computer or
number generator
– It is used when you have an accurate and
easily accessible sampling frame that lists the
entire population.
– Tool: lottery method
11/15/24 Ali Yassin Sheikh, PhD 15
 Probability Sampling, cont…
• Stage three cont…
– Systematic sampling: involves selecting the
sample at regular intervals from the sampling
frame.
– Stratified random sampling: you divide the
population into two or more relevant and
significant strata based on one or a number of
attributes/ features.

11/15/24 Ali Yassin Sheikh, PhD 16

 Systematic sampling

Stratified random sampling

11/15/24 Ali Yassin Sheikh, PhD 17

 Probability Sampling, cont…
• Stage three cont…
– Cluster sampling: dividing the sample into
separate groups prior to sampling (e.g., type
of businesses or geographical area).
– Multi-stage sampling (or multi-stage cluster)
reaching to individuals: involves taking a
series of cluster samples, each involving
some form of random sampling.

11/15/24 Ali Yassin Sheikh, PhD 18

11/15/24 Ali Yassin Sheikh, PhD 19
 Non-probability Sampling
• Non-probability sampling techniques:
– Are appropriate for studies which don’t have
sample frames (population).
– It provides a range of alternative techniques
to select samples based on your subjective
judgement.
– It is practical for exploratory studies
– It will not allow “the extent of the problem” to
be determined.
11/15/24 Ali Yassin Sheikh, PhD 20
 Non-probability Sampling, cont…
• Non-probability sampling techniques:
– Quota sampling: a type of stratified sample in
which selection of cases within strata is
entirely non-random.
• it is normally used for interview surveys.
• It is normally used for large populations.
• Your choice is dependent on two main factors:
– Usefulness as a means of stratifying the data
– Ability to overcome likely “variations between groups” in
their availability for interview

11/15/24 Ali Yassin Sheikh, PhD 21

 Non-probability Sampling, cont…
– Purposive sampling (judgement):
• Enables you to use your judgement to select cases
that will best enable you to answer your research
questions.
• It is often used when working with very small
samples.

11/15/24 Ali Yassin Sheikh, PhD 22

 Non-probability Sampling, cont…
• Snowball sampling:
– is common used when it is difficult to identify
members of the desired population
• (e.g., people who are working while claiming
unemployment benefit).
• Self-selection sampling:
– Occurs when you allow each case to identify
their desire to take part in the research.

11/15/24 Ali Yassin Sheikh, PhD 23

 Non-probability Sampling, cont…
• Convenient sampling (or haphazard):
– Involves selecting haphazardly those cases
that are easiest to obtain for your sample.
• e.g., the person interviewed at random in a
shopping centre for a television program.
– The sample selection process is continued
until your required sample size has been
reached.

11/15/24 Ali Yassin Sheikh, PhD 24

 Conclusion
• A well described sampling technique should:
– Select your sample based on two way:
• From the literature
• Through calculation – using formula
– Develop Criteria for selecting the sample size
– Name the sampling technique
– Describe the main features of the sampling
technique
– Provide a justification for selecting the sampling
technique for the study
– State the purpose (use) of the technique in the
11/15/24 study Ali Yassin Sheikh, PhD 25
Example 1
Sample procedure
• The study were used both probability and non probability
sampling techniques to create a sampling frame. In
probability sampling use stratified sampling to ensure
that different gender of students would be included in the
survey. Once strata are identified then use non
probability sampling to carry out the real study.
• The researchers used judgmental sampling techniques
of non-probability sampling because the researchers
cannot obtain the list of student names from the
university. Therefore, data was collect from those
students who were conveniently available and willing to
co-operate.
11/15/24 Ali Yassin Sheikh, PhD 26
Example 2
Sample procedure
• This study employed non- probability sampling, the
purposive sampling technique will be selected. In the
purposive sampling, the researchers decided who can
participate the sample; the researchers chose this
method because it reduces time and money
consumption.

11/15/24 Ali Yassin Sheikh, PhD 27