Assignment of:
Basic Epidemiology
Submitted by:
Usama Rafiq
Submitted to:
Ma’am Safina
Registration no:
70110120
Department:
Public Health (semester 8th)
Date:13/08/2024.
Difference between probability and non probability.
What is Probability Sampling?
Probability sampling is a sampling strategy in which each member of a population has an
equal and known chance of being chosen. The goal of this approach is to get a representative
sample that correctly represents the makeup and features of the full population. Simple random
sampling, systematic sampling, stratified sampling and cluster sampling are the four main
methods of probability sampling.
What is Non-Probability Sampling?
On the other hand, non-probability sampling does not offer every individual an equal chance
of selection. Instead, elements are selected based on their accessibility or the researcher's
judgment. Convenience sampling, purposive sampling, quota sampling, and snowball sampling
are examples of non-probability sampling methods.
Difference between Probability Sampling and Non probability Sampling:
Probability Sampling Non-Probability Sampling
Based on random selection Based on non-random selection
Each member has a known chance of selection Unequal chance of selection
Enables statistical inference Limited statistical inference
Provides unbiased estimates Potential for bias in estimates
Uses random sampling techniques Uses non-random sampling techniques
Requires sampling frame Sampling frame might not be necessary
Representative of the population Might not represent the entire population
Allows for calculation of sampling error Sampling error calculation might not be
straightforward
Examples: Simple Random, Systematic, Examples: Convenience, Judgmental, Quota
Stratified sampling sampling
High external validity Limited external validity
Time-consuming and costly Generally quicker and more cost-effective
Complex analysis due to known probabilities Simplified analysis due to unknown or varying
probabilities
Appropriate for large populations Suitable for smaller populations
Provides a more objective selection process Subjective selection process
Minimizes researcher bias Researcher bias might impact sample selection
Requires a random number generator No need for a random number generator
Examples: Random Cluster, Systematic, Examples: Convenience, Judgmental, Snowball
Stratified sampling sampling
Less room for researcher manipulation More room for researcher manipulation
Clear inclusion and exclusion criteria Criteria might not be clearly defined
Generalizability of results Limited generalizability of results
Well-defined sampling process Sampling process might not be well-defined
Common in quantitative research Common in exploratory or qualitative research
Requires a sampling plan Sampling plan might not be necessary
Strengthens statistical validity Weaker statistical validity
Higher chance of sample being representative Sample might not accurately represent the
population
Examples: Simple Random, Stratified, Cluster Examples: Convenience, Snowball, Purposive
sampling sampling
Randomization reduces bias Potential bias due to non-randomization
Appropriate for hypothesis testing Less suitable for hypothesis testing
Allows for margin of error calculation Margin of error calculation might not be
applicable
Write examples of Non-random sampling:
Non-random sampling methods, also known as non-probability sampling methods, involve
selecting samples based on subjective judgment rather than random selection. Here are some
examples:
1. Convenience Sampling
Example: A researcher stands outside a shopping mall and interviews the first 50 people
who pass by. This method is chosen because it is easy and quick, but it may not represent
the broader population.
2. Purposive (Judgmental) Sampling
Example: A researcher studying the impact of a specific drug selects only patients who
have been taking the drug for more than six months. The sample is chosen based on the
specific characteristics relevant to the study.
3. Quota Sampling
Example: A market researcher needs to interview 100 people, with 50 males and 50
females. The researcher continues interviewing until the quota for each group is met,
regardless of how the participants are chosen.
4. Snowball Sampling
Example: In a study on homelessness, a researcher starts by interviewing a few known
homeless individuals and then asks them to refer others who are also homeless. The
sample grows like a "snowball" through referrals.
5. Judgmental Sampling
Example: A teacher wants to evaluate the effectiveness of a new teaching method and
selects the top-performing students in the class to test it. The selection is based on the
teacher's judgment rather than random selection.
6. Voluntary Sampling
Example: An online survey about customer satisfaction is posted on a company's website,
and only those who visit the website and choose to participate are included in the study.
This method relies on participants' willingness to respond.
