Sampling Methods in Statistics: Probability and Non Probability
Approaches
In research, it is often impractical to collect data from every member of a population due to
constraints of time, cost, and accessibility. Sampling methods provide systematic
procedures to select a subset of individuals or items (the sample) from a much larger
population. This allows researchers to make inferences about the population without
examining every member, while reducing resources and avoiding unnecessary procedures
in fields such as healthcare and ultrasound imaging (Elfil & Negida, 2017; Taherdoost,
2016).
Sampling methods fall broadly into two categories: probability and non probability
sampling. In probability sampling, every member of the population has a known, non zero
chance of being selected, allowing for statistical inference and measurable sampling error
(Lohr, 2022). In non probability sampling, selection is not random; although often quicker
and more practical, it limits generalisability and the ability to estimate sampling error
(Taherdoost, 2016).
This paper integrates detailed explanations of both approaches using examples relevant to
ultrasound research, and draws upon the definitions and strengths/weaknesses outlined in
Taherdoost (2016). It also incorporates insights from recent clinical research reviews to
enhance applicability (Suresh et al., 2012; Elfil & Negida, 2017).
Probability Sampling
Probability sampling ensures that each member of the population has a defined and non
zero probability of inclusion. This minimises selection bias, enhances representativeness,
and supports statistical analysis, such as hypothesis testing and confidence interval
estimation (Lohr, 2022; Taherdoost, 2016). The process involves defining the target
population, constructing a sampling frame, and applying a random selection method
(Thompson, 2012). In clinical research, including ultrasound studies, these methods are
preferred for their ability to produce unbiased results and allow for valid inferences (Suresh
et al., 2012).
a) Simple Random Sampling
Definition: Every member ... (content shortened for brevity).
b) Systematic Sampling
Definition: Selecting every kth individual ...
c) Stratified Sampling
Definition: Dividing the population into homogeneous subgroups ...
d) Cluster Sampling
Definition: Dividing the population into clusters ...
Non Probability Sampling
Non probability sampling does not use random selection. Participants are chosen based on
accessibility, judgement, or referral. This approach is quicker and more practical, but limits
generalisability and prevents precise error estimation (Taherdoost, 2016). It is especially
useful in situations where the population is hard to define or access, such as in preliminary
studies, pilot trials, or when dealing with sensitive topics in healthcare.
a) Convenience Sampling
Definition: Selecting participants who are easiest to access ...
b) Purposive Sampling
Definition: Selecting participants with specific characteristics relevant to the study ...
c) Snowball Sampling
Definition: Using initial participants to recruit others who meet the study criteria ...
d) Quota Sampling
Definition: Selecting participants until pre set quotas for subgroups are filled ...
Sample Size Considerations in Ultrasound Research
In ultrasound studies, choosing a sampling method must also consider sample size to
ensure statistical power. Recent reviews show that trials on point of care ultrasound often
underestimate sample sizes, leading to inconclusive results (Ibrahim et al., 2025).
Conclusion
Both probability and non probability sampling methods have unique strengths and
weaknesses. Probability sampling offers greater representativeness and supports statistical
inference, making it ideal for large scale, guideline informing research. Non probability
sampling, while less generalisable, provides practical options for exploratory research, rare
conditions, and preliminary studies by allowing faster, targeted data collection with careful
bias management. The choice depends on research aims, resources, and the required level
of precision (Taherdoost, 2016).
References
Ackoff, R. L. (1953). The design of social research. Chicago: University of Chicago Press.
Breweton, P., & Millward, L. (2001). Organizational research methods. London: SAGE.
Davis, D. (2005). Business research for decision making. Australia: Thomson South Western.
Elfil, M., & Negida, A. (2017). Sampling methods in clinical research; an educational review.
Emergency, 5(1), e52.
Ghauri, P., & Gronhaug, K. (2005). Research methods in business studies. Harlow:
FT/Prentice Hall.
Ibrahim, M., et al. (2025). Sample Size of Trials Investigating the Impact of Point‐of‐Care
Ultrasound: A Scoping Review. Journal of Ultrasound in Medicine.
Lohr, S. (2022). Sampling: Design and analysis (3rd ed.). CRC Press.
Maxwell, J. A. (1996). Qualitative research design: An interactive approach. London: Applied
Social Research Methods Series.
SAT0666 Sample size for RA clinical trials using ultrasound. (2017). Annals of the
Rheumatic Diseases.
Suresh, K., Thomas, S. V., & Suresh, G. (2012). Design, data analysis and sampling techniques
for clinical research. Annals of Indian Academy of Neurology.
Taherdoost, H. (2016). Sampling methods in research methodology; how to choose a
sampling technique for research. International Journal of Academic Research in
Management, 5(2), 18–27.
Thompson, S. K. (2012). Sampling (3rd ed.). John Wiley & Sons.