Abstraction Topic2 Sampling Techniques

ELEMENTARY STATISTICS AND PROBABILITY
Topic 2:
SAMPLING TECHNIQUES
Data collection is the method of collecting and evaluating information on the target variables.
Well-chosen and well-established methods of data collection and interpretation are important so
that you can present the data with soundness and consistency. In this topic on data collection and
presentation, we will work on how we can perform collection and presentation of the data
available. The following are the learning objectives.
Learning Outcomes:
At the end of this topic, you must be able to:
1. Explain sampling techniques and its relevance in data collection; and

2. Present quantitative and qualitative data.
In statistics, there are different types of sampling especially if the population under study is large.
It is good to get samples in order to be effective, efficient and economical in data gathering. There
are two major classifications of sampling: probability and non-probability.
1. Probability Sampling
• It is a method of sampling where it utilizes some form of random selection so that units
in the population have equal chances of being part of the sample.
• There are five (5) types of probability sampling namely: simple random sampling,
systematic random sampling, stratified random sampling cluster sampling, and
multistage sampling.
•
Simple Random Sampling (SRS)
• Simplest form of random sampling.

• Selection of the sample may be done into two ways: without replacement and
with replacement.
o In simple random sampling without replacement (SRSWOR), units
selected once are not returned to the population.
o In simple random sampling with replacement (SRSWR), units selected are
returned to the population.
• Common technique of drawing a sample is lottery or fishbowl technique.
• Procedure in Simple Random Sampling:
1. Identify the units in the population.
2. Assign a code to each units of the population.
3. Select N sample needed in the study:
o for SRSWOR, once drawn it will be removed; and
o for SRSWR, it is returned and can be part of the sample more than one.
ORDIZ, J.E.G. (2020) Page | 1

Figure 7. Illustration of SRSWOR using fish bowl technique
Figure 8. Illustration of SRSWR using fish bowl technique
Systematic Random Sampling
• Selection is done through listing by arranging units systematically or logically.

• Commonly used as alternative to simple random sampling.
• A method where a sample is taken in every kth unit from the ordered population,
where only the first unit is being selected at random and the rest will be
systematic.
• Procedure in Systematic Random Sampling:
1. Arrange the units in order (either increasing or alphabetical or any
acceptable arrangement).
2. Determine the sampling interval using the formula 𝑘 = 𝑁/𝑛. Where k is the
sampling interval, N is the population size, and n is the sample size.
3. Select a number at random from 1 to k and will be your first sample.
4. Select other sample systematically through the sampling interval k. Every
kth will be your next sample until completed the desired sample size.

Figure 9. Illustration of Systematic Random Sampling with k at every 3rd unit
Stratified Random Sampling
• Population is clearly divided into a number, L, which is non-over-lapping.

• Groups are referred to as strata (statum).
• Process of grouping the population into strata is called stratification.
• Samples within strata are more or less homogeneous.
• Samples among strata are most heterogeneous.
• In stratified random sampling, the probabilities of selection may be same from
strata to strata, or they may be different.
• Two main reasons for choosing stratified random sampling:
o Assures to represent not just the overall population but also subgroups of
the population; and
o Statistically precise compared to simple random sampling.
• Procedure in Stratified Random Sampling:

1. Stratify the units of the population into strata according to their
homogeneity or similarity.
2. Make sure each stratum is heterogeneous or diverse from each other.
3. Use either simple random sampling or systematic random sampling to get
the desired sample size.

Figure 10. Illustration of Stratified Random Sampling with two units per strata using SRS
Cluster Sampling
• Used when population is very large and widely spread out over a wide range of
geographical area.
• Population of N is divided into M clusters, which may not be the same in size.
• Clusters are mutually exclusive sub-populations which together comprise the
entire population. Clusters are preferably formed with heterogeneous rather
than homogeneous members so that cluster will be a typical population.
• If all members of the selected cluster are included as sample, then it is called one-
stage cluster sampling. If we take a random sample of each selected cluster, then
it is called two-stage cluster sampling.
• Cluster generally results larger sampling error than simple random sampling.
• Procedure in Cluster Sampling:

1. Determine the cluster present in your population by geographical area.
2. Make sure units in every cluster is heterogeneous.
3. Select randomly which cluster to become your sample.
4. Decide whether to use one stage or two stage sampling.

Figure 11. Illustration of One-Stage Cluster Sampling
2. Non-Probability Sampling
• It is a method of sampling which does not involve random selection, thus the population
has not given equal chance of being included in the sample.
• There are at least four (4) methods of non-probability sampling namely: convenience
sampling, snowball sampling, purposive sampling, and quota sampling.
Convenience Sampling
• Involves collecting a sample from somewhere convenient to you.
Figure 12. Illustration of Convenience Sampling with black circle represent the
researcher choosing the respondents conveniently

Snowball Sampling
• Research participants recruit other members for the study. This method is
particularly useful when participants might be hard to find. For example, a study
on working prostitutes or current heroin users.
Figure 12. Illustration of Snow Sampling with black circle represent the researcher
choosing the respondents and the respondents refer other respondent
Purposive Sampling
• Researcher chooses a sample based on their knowledge about the population

and the study itself. The study participants are chosen based on the study’s
purpose.
Figure 13. Illustration of Purposive Sampling with black circle represent the researcher
choosing the respondents and the respondents based on study’s purpose

Quota Sampling
• Groups (i.e. men and women) in the sample are proportional to the groups in the
population. There is a fixed quota and the main concern of the researcher is to
meet the required number of samples no matter how they are selected.
Figure 14. Illustration of Quota Sampling with black circle represent the researcher
choosing five (5) respondents regardless of selection guidelines
References
1. ICLYouGov (2020, July 17). Covid-19 Behavior Tracker. Tableauu public. Retrieved from
https://public.tableau.com/profile/ighi#!/vizhome/ICLYouGovCovid-
19Tracker_V0_3/1Specificpreventativebehaviourbycountry
2. Alferez, M. & Duro, C. (2006). Statistics and Probability. MSA Academic Advancement
Insitute. MSA Publishing House.
3. Asaad, A. (2008). Statistics: Made Simple for Researchers. REX Book Store Inc.
4. Simple Random Sampling (n.d.).Retrieved from

http://home.iitk.ac.in/~shalab/sampling/chapter2-sampling-simple-random-
sampling.pdf.
5. Stephanie Glen. "Non-Probability Sampling: Definition, Types" From

StatisticsHowTo.com: Elementary Statistics for the rest of us!
https://www.statisticshowto.com/non-probability-sampling/

Abstraction Topic2 Sampling Techniques

Uploaded by

Copyright:

Available Formats

Abstraction Topic2 Sampling Techniques

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Abstraction Topic2 Sampling Techniques

Uploaded by

Copyright:

Available Formats

ELEMENTARY STATISTICS AND PROBABILITY

At the end of this topic, you must be able to:

1. Explain sampling techniques and its relevance in data collection; and

Simple Random Sampling (SRS)

• Simplest form of random sampling.

ORDIZ, J.E.G. (2020) Page | 1

Figure 7. Illustration of SRSWOR using fish bowl technique

Figure 8. Illustration of SRSWR using fish bowl technique

Systematic Random Sampling

• Selection is done through listing by arranging units systematically or logically.

ORDIZ, J.E.G. (2020) Page | 2

Figure 9. Illustration of Systematic Random Sampling with k at every 3rd unit

Stratified Random Sampling

• Population is clearly divided into a number, L, which is non-over-lapping.

• Procedure in Stratified Random Sampling:

ORDIZ, J.E.G. (2020) Page | 3

• Procedure in Cluster Sampling:

ORDIZ, J.E.G. (2020) Page | 4

Figure 11. Illustration of One-Stage Cluster Sampling

• Involves collecting a sample from somewhere convenient to you.

ORDIZ, J.E.G. (2020) Page | 5

• Researcher chooses a sample based on their knowledge about the population

ORDIZ, J.E.G. (2020) Page | 6

4. Simple Random Sampling (n.d.).Retrieved from

5. Stephanie Glen. "Non-Probability Sampling: Definition, Types" From

ORDIZ, J.E.G. (2020) Page | 7

You might also like