Picking out the right sample for your survey

Survey

In an ideal world, a survey would collect data from every individual in a population. However, in most cases this isn’t feasible because of limited resources and time. So we need to use a subset of the population to draw a conclusion.

Identifying the right subset of population to work with is an art. This should be a carefully identified group that is representative of the whole population.

Why is sampling so important?

Sampling a part of the population often works as a more effective surveying tool than a full-blown census, which involves interviewing everyone in a population. You can examine a single area in greater depth with a smaller sample, as opposed to trying to find patterns in a huge pool of data. The latter is like trying to find a needle in a haystack.

Did you know? Sampling and surveying a representative part of the population is often more effective than asking everyone.
There are many different sampling methods, and which one you choose will depend on the sampling techniques, the context, your research purpose, and various other factors.

Before we dive into the sampling techniques, there are three things to keep in mind while constructing a sample:

Diversity
Ensuring that all units in the survey are not similar to each other is a tall order, but it's important. To be a truly representative sample, the entire group must represent the spectrum of diversity within the population.
Consistency
It's also important that survey respondents have been tracked on a case-by-case basis before going ahead with the survey. A good idea is to administer a consistency test for a sample, for example a pilot test, where you compare the individual units of the sample with the whole to make sure it properly represents the parent population's characteristics.
Transparency
Many factors determine the size and the structure of a population. Researchers need to discuss these limitations and maintain transparency about the procedures followed while selecting the sample so the survey results are viewed with the right perspective.

Now let's get to the different sampling techniques.

Sampling techniques

Sampling methods can be categorized under two main headers: probability sampling and non-probability sampling.

Probability sampling techniques
Random sampling
Systematic sampling
Stratified sampling
Non-probability sampling techniques
Judgement sampling
Snowball sampling
Quota sampling
Convenience sampling

Probability sampling techniques

This happens when each entity of the survey has a definite, non-zero probability of being incorporated into a sample. We call this a "definitive sample".

Probability samples are selected to be highly representative of the population. This way, they provide the most valid or credible results because they reflect the characteristics of that particular population.

There are three main kinds of probability sampling techniques: random, systematic, and stratified.

Random sampling

When This is the most straighforward sampling method. Random sampling is used with vast populations where every member is chosen independently from the rest.
How This technique is easy to conduct because each subject is selected independently of the other members of the population.

Pros: Each member of the population has an equal chance of getting selected.

Cons: The sample can easily become biased.

Use case: If we know the census data of a town has the population of men and women spread into 50:50, but we happen to have collected data for 200 men and 100 women, we can use stratified sampling to adjust this difference and maintain this ratio.

Systematic sampling

When In cases where our population is logically homogenous.
How In this method, we are viewing our sample as logically homogenous - i.e, all the units in the population attribute an equal interest for the surveyor. This technique involves ordering all individuals in a sequence and selecting individuals from regular intervals—say every fifth element in the set.

Pros: Systematic sampling is advantageous over random sampling because of its simplicity. Also, this process ensures that the population will be evenly sampled. Clustered selection of subjects can be avoided through this method.

Cons: The possible weakness of the method is that the periodic nature of the list may compromise the randomness of the sample. Because of the periodic nature of the sampling, this may also be subject to bias. This can be avoided by randomizing the population entities—similar to how you would shuffle a deck of cards—before you proceed with systematic sampling.

Use case: If the population you’re studying is customers who visit a coffee shop on weekday mornings, the characteristics of this homogeneity would be:

Customers of the coffee shops
People who visit on weekday mornings.

Stratified sampling

When In cases where you can divide your population into characteristics of importance for research.
How Stratified sampling involves splitting the population into layers according to one or several characteristics. The intention here is to attempt to recreate the statistical features of the population on a smaller scale. Before sampling, the target population is divided into characteristics of importance for research: for example, by gender, social class, education level, religion, etc. Then the sample is created to simulate the target population.

Pros: Stratified sampling tries to overcome the disadvantage of the other two methods of sampling. This method ensures that all sections of the population are equally represented. It is used when one or more sections in the sample have a low incidence relative to the other sections.

Cons: It requires prior knowledge of the proportion of the different subgroups in the population. Also, it is the most complex method of sampling and lays down criteria that may be difficult to fulfill while placeing heavy strain on available resources.

Non-probability sampling techniques

Non-probability sampling techniques are the opposite of probabily sampling techniques in that it gives individuals in the sample an unequal chance of being selected.

Most surveys are not based on probability techniques, but rather on finding a suitable collection of respondents to complete the survey. In non-probability sampling, the relationship between the target population and the survey sample is immeasurable and the potential bias cannot be measured.

In these techniques, the selection is not completely randomized, thus the resultant sample is not truly representative of the entire population.

Judgement sampling

When The researcher decides which population they want to include in a sample based on his existing knowledge or professional judgement. It’s alternatively also called as purposive sampling.

Pros: The researcher may provide some alternate justification for the representativeness of the sample and has complete freedom to define its composition.

Cons: The underlying assumption of judgement bias is that the investigator will select units that are characteristic of the entire population set. For this reason, this sampling method is subject to bias.

Use case: A researcher tries to find out a correlation between people who wear eyeglasses and their tendency to read books. In common sense, it is quite evident that they should only focus on people who wear glasses. By targeting a common population of people who only wear glasses, people have a higher chance to achieve their surveying goal.

Snowball sampling

When This technique is used when the target population is rare. Members of the target population recruit other members of the population for the survey.
How Just as snowballs roll in and gather mass, a sample constructed in this way will grow as you move through the process of conducting the survey.

Pros: The costs associated with this process are lower, and you're likely to end up with a sample that is representative of your study.

Cons: The surveyor might end with a small, largely homogenous section of the population.

Use case: Snowball sampling can come in handy when you need the sample to reflect some features that are difficult to find. It can also come in handy for repetitive activities. To conduct a survey of people who go jogging in a certain park every morning, a snowballing technique would be a quick and accurate way to create a sample.

Quota sampling

When The sample is designed to include a designated number of people with certain specified characteristics.
How Quota sampling is the non-probability equivalent of stratified sampling that we discussed earlier. It starts with characterizing the population based on certain desired features and assigns a quota to each subset of the population.

Pros: The process can be extended to cover several characteristics and several degrees of complexity.

Cons: Though it is considered superior to convenience and snowball sampling, it fails to offer the statistical insights of any of the probability methods.

Use case: A situation where an interviewer has to survey people about a certain cosmetic brand, and his target population is people in a certain age group between 35-45 years. After choosing this, the surveyor can decide according to his convinience which people to choose according to the quota and from where.

Convenience sampling

When During preliminary research efforts.
How This sample is composed of, as the name suggests, people who are conventient to contact. Whoever persons are easily accessible are selected to complete the survey.

Pros: The sample is created quickly without adding any additional burden on available resources.

Cons: Because those who are easily available are selected, the likelihood of the sample being representative of the population is poor.

Use case: This method is used quite often during preliminary research efforts to get a gross estimate of the results without incurring the cost or the time necessary to select the population.

For the inital stages, probability sampling can have some sense of superiority, but its costs can be prohibitive. During these early stages of a study, non-probability techniques are probably a better way to give you an idea of what you are dealing with.

Once you have successfully selected your sample, you can start surveying by selecting from any of Zoho Survey’s 200 expert-verified templates and choosing from our list of 25 different question types.

Happy surveying!

Identifying theright sampling method for your survey