When conducting research on a group of people, it is rarely possible to collect data from all the people in that group. Instead, sampling is done. The sample is the group of individuals who will actually participate in the research.
To draw valid conclusions from your results, you need to carefully decide how you are going to select a sample that is representative of the group as a whole. According to Edwards (2014), there are two types of sampling methods:
Probabilistic sampling involves random selection, allowing you to make solid statistical inferences about the entire group.
Non-probabilistic sampling involves non-random selection based on convenience or other criteria, allowing you to easily collect data.
You should clearly explain how you selected the sample in the methodology section of your work or thesis.
Population vs. sample
First, according to Pyrczak (2014), you have to understand the difference between a population and a sample, and identify the target population of your research.
The population is the whole group on which you want to draw conclusions.
The sample is the specific group of individuals from which data are collected.
Population can be defined in terms of geographic location, age, income and many other characteristics.
It can be very broad or quite limited: you may want to make inferences about the entire adult population of your country; perhaps your research focuses on the customers of a certain company, on patients with a particular disease or on students in a single school.
It is important to carefully define the target population according to the objective and practical aspects of the project.
If the population is very large, demographically mixed and geographically dispersed, it may be difficult to access a representative sample.
The sampling frame is the actual list of individuals from which the sample will be extracted. Ideally, it should include the entire target population (and no one who is not part of that population).
You are conducting research into working conditions in company X. Its population is the 1,000 employees of the company. The sampling frame is the company’s human resources database, which contains the names and contact details of all employees.
The number of people to include in the sample depends on several factors, such as population size and variability and research design. There are different calculators and sample size formulas depending on what you want to achieve with statistical analysis.
Probabilistic sampling methods
Probabilistic sampling means that each member of the population has a chance of being selected. It is mainly used in quantitative research. According to Joyner et al (2013), if you want to obtain results representative of the entire population, probabilistic sampling techniques are the most valid option.
There are four main types of probabilistic sampling.
Simple random sampling
In a simple random sampling, each member of the population has the same probability of being selected. The sampling frame must include the entire population.
To perform this type of sampling, you can use tools such as random number generators or other techniques that are based entirely on chance.
You want to select a simple random sample of 100 employees from company X. Each employee in the company database is assigned a number from 1 to 1000, and a random number generator is used to select 100 numbers.
Systematic sampling is similar to simple random sampling, but is usually somewhat easier to perform. Each member of the population appears with a number, but instead of generating random numbers, individuals are chosen at regular intervals.
All employees of the company are listed in alphabetical order. From the first 10 numbers, a starting point is randomly selected: the number 6. From number 6, every 10 people are selected from the list (6, 16, 26, 36, etc.), and a sample of 100 people is finished.
If you use this technique, it is important to make sure that there are no hidden patterns in the list that can skew the sample. For example, if the HR database groups employees by teams, and team members appear in order of seniority, there is a risk that their range will omit people in lower roles, resulting in a skewed sample of older employees.
Stratified sampling consists of dividing the population into subpopulations that may differ in important respects. It allows more precise conclusions to be drawn by ensuring that each subgroup is adequately represented in the sample.
To use this sampling method, the population is divided into subgroups (called strata) based on the relevant characteristic (for example, sex, age range, income level, or job function).
Based on the overall proportions of the population, the number of people to be sampled from each subgroup is calculated. Random or systematic sampling is then used to select a sample from each subgroup.
The company has 800 employees and 200 employees. He wants to make sure that the sample reflects the gender balance of the company, so he classifies the population into two strata based on gender. It then uses random sampling in each group, selecting 80 women and 20 men, which gives it a representative sample of 100 people.
Cluster sampling also involves dividing the population into subgroups, but each subgroup must have characteristics similar to those of the entire sample. Instead of sampling individuals from each subgroup, entire subgroups are randomly selected.
If possible in practice, you can include all individuals from each sampled cluster. If the clusters are large, you can also sample individuals from each cluster using one of the above techniques.
This method is good for dealing with large and dispersed populations, but there is a higher risk of error in the sample, as there could be substantial differences between clusters. It is difficult to guarantee that the sampled clusters are truly representative of the entire population.
The company has offices in 10 cities across the country (all with approximately the same number of employees with similar functions). It does not have the ability to travel to all offices to collect data, so it uses random sampling to select 3 offices, which are its clusters.
A convenience sample simply includes the individuals who are most accessible to the researcher.
It is an easy and inexpensive way to collect initial data, but there is no way to know if the sample is representative of the population, so it cannot produce generalizable results.
You’re researching opinions about student support services at your university, so after each of your classes, you ask your peers to complete a survey on the topic. This is a convenient way to collect data, but because you only surveyed students who took the same classes as you at the same level, the sample is not representative of all students at your university.
Voluntary response sampling
Like the convenience sample, the voluntary response sample is primarily based on ease of access. Instead of the researcher choosing participants and contacting them directly, people volunteer (for example, by responding to an online public survey).
Voluntary response samples are always at least somewhat biased, as some people will be inherently more likely to volunteer than others.
You send the survey to all students at your university and many of them decide to complete it. This can certainly give you an idea of the topic, but the people who responded are more likely to be those who have strong opinions about student support services, so you can’t be sure that their opinions are representative of all students.
This type of sampling, also known as trial sampling, involves the investigator using his or her experience to select a sample that is most useful for the purposes of the investigation.
It is often used in qualitative research, when the researcher wants to gain detailed knowledge about a specific phenomenon rather than making statistical inferences, or when the population is very small and specific. An effective intentional sample must have clear criteria and justification for inclusion.
You want to know more about the opinions and experiences of disabled students at your university, so you intentionally select several students with different support needs in order to collect a varied range of data about their experiences with student services.
If the population is hard to access, snowball sampling can be used to recruit participants through other participants. The number of people you have access “snowballs” as you come into contact with more people.
You are researching the experiences of the homeless in your city. As there is no list of all homeless people in the city, probabilistic sampling is not possible. You meet a person who agrees to participate in the research and puts you in touch with other homeless people you know in the area.
Non-probabilistic sampling methods
according to Cottrell (2014), in a non-probabilistic sampling, individuals are selected based on non-random criteria, and not all individuals have the possibility of being included.
This type of sample is easier and cheaper to access, but has a higher risk of sampling bias. This means that the inferences you can make about the population are weaker than with probabilistic samples, and your conclusions may be more limited. If a non-probabilistic sample is used, we must try to make it as representative as possible of the population.
Non-probabilistic sampling techniques are often used in exploratory and qualitative research. In these types of research, the goal is not to test a hypothesis about a large population, but to develop an initial understanding of a small or under-researched population.
Our specialists wait for you to contact them through the quote form or direct chat. We also have confidential communication channels such as WhatsApp and Messenger. And if you want to be aware of our innovative services and the different advantages of hiring us, follow us on Facebook, Instagram or Twitter.
If this article was to your liking, do not forget to share it on your social networks.
You may be also interested in: Non-Experimental Research
Cottrell, Stella. Dissertations and Project Reports: A Step by Step Guide. Basingstoke, UK: Palgrave Macmillan, 2014.
Edwards, Mark. Writing in Sociology. Thousand Oaks, CA: Sage Publications, 2014.
Joyner, Randy L., William A. Rouse, and Allan A. Glatthorn. Writing the Winning Thesis or Dissertation: A Step-by-step Guide. 3rd edition. Thousand Oaks, CA: Corwin Press, 2013.
Pyrczak, Fred. Writing Empirical Research Reports: A Basic Guide for Students of the Social and Behavioral Sciences. 8th edition. Glendale, CA: Pyrczak Publishing, 2014.