Things You Need To Know About Survey Sample Size

What you'll learn

By the end of this lesson, you'll be able to:

• Understand sample size and why choosing the right one matters.
• Calculate a survey sample size using a set formula.
• Understand the different types of sampling techniques.

1. What is a survey sample size?

You may want opinions from 50 people, or from 50 thousand. Asking 50 people is easier than asking 50 thousand.

So what do you do when you need the opinion of 50 thousand people? That is where survey sample size comes in.

The survey sample size is a smaller number of people whose collected opinions can accurately represent the opinion of the entire targeted population of your survey.

2. Why choosing the right sample size matters

Sample size is a key consideration in survey design, because it directly affects the accuracy and reliability of the results.

A small sample size can lead to biased or unreliable findings, since it may not represent the larger population being studied. A large sample size can give more accurate and generalizable results, but it costs more and is time-consuming to collect.

A well-designed survey should aim to balance sample size and cost. The sample needs to be large enough to represent the population, but not so large that it becomes impractical.

When you size the sample carefully, the results are accurate and actionable, and they give you insights you can use to make decisions.

So what counts as a good sample size?

3. Choosing a good sample size

• Minimum sample size: The general view is that the sample size should be a minimum of 100. This means that if your total survey population is less than 100, you must survey the whole population.
• Maximum sample size: Another general view is that your sample size should be 10% of your total population and, at the same time, not exceed 1000. The higher your sample size, the longer the survey takes. For example, if your survey population is 50000, then 10% of that is 5000, which exceeds the 1000 threshold. In this case, let your sample size be 1000.

There are no hard and fast rules for determining the sample size, but there is a mathematical formula to calculate it.

The next section walks through that calculation.

4. How to calculate the survey sample size

As mentioned earlier, calculating the survey sample size involves a mathematical formula.

These are the terms used in the formula.

• Population Size (N) is the total number of people in your population. For example, if you are surveying an organization, the population size is the total number of employees in it.

• Confidence level & z-score (z) is how confident you are that the responses you collect are accurate. The confidence level is usually given as a percentage.

  You turn your confidence level into a z-score (z) using the table below. For example, the 95% confidence level has a z-score of 1.96.

• Margin of error (ε) is how much error you will allow in your survey.

  Errors are unavoidable, which is why the error margin exists.

  It is given as a percentage.

• Standard deviation (p^) is how confident you are that the population selects an answer within a given range.

  A lower standard deviation means you don't expect your respondents to choose extreme answers.

  A higher standard deviation means you expect respondents to choose answers from the ends of the spectrum.

  Standard deviation is given as a number between 0 and 1. If you are unsure what to choose, go with 0.5, the exact midpoint.

With all the inputs ready, you can calculate the sample size using the formula in the screenshot below.

You can also check out the sample size calculator from BlockSurvey, below.

BlockSurvey sample size calculator

The calculator is easier and faster.

The next section has a worked example of the calculation.

5. A worked example

When you know the total population size, you can use the BlockSurvey Sample Size calculator mentioned in the previous section to find your sample size.

When your target population is unlimited or unknown, you can use the mathematical formula shown in the screenshot in the previous section.

Assume you have

• 95% confidence level (the corresponding z-score is 1.96)
• 0.5 standard deviation (midpoint chosen)
• 5% margin of error

The calculation goes like this.

((z-score)2 x standard-deviation(1-standard deviation)) / (margin of error)2

((1.96)2 x .5(.5)) / (.05)2

(3.8416 x .25) / .0025

.9604 / .0025

384.16 ~ 385

385 respondents are needed.

That is it. You have just learned how to determine a sample size.

Since 385 is a surveyable population, we will stop here rather than move to the next formula.

6. Use case based sample size

Below is a table that shows the accuracy of the results.

The larger the sample size, the greater the accuracy of the results.

A sample size with greater accuracy is called a statistically significant sample size*.*

Here are use cases that need a statistically significant sample size and ones that do not.

• Employee Surveys: Employee surveys in organizations gather feedback on work culture. You want a holistic view of all employees.

  In that case, a statistically significant sample size is required.

• Customer Surveys: Customer surveys usually arrive case by case rather than in a single bulk. Here, every customer's feedback is valuable on its own, so a statistically significant sample size is not required.

• Healthcare Surveys: Take 2 healthcare surveys as examples: a drug discovery survey and a patient feedback survey. Drug discovery needs a holistic view, so a statistically significant sample size is required. For patient feedback, a significant sample size is not very important.

• Market Surveys: Market research surveys and poll surveys need a holistic view to make decisions. Like employee surveys, market surveys need statistically significant sample sizes to get an overall opinion of the entire target population.

• Education Surveys: If the purpose of your education survey is to change the school or college system, then a statistically significant sample size is important. If the purpose is just to learn what a student thinks about the school and teachers, then it is not very important.

• Casual Surveys: If you just want to survey friends and relatives for fun, you can ignore the significant sample size and enjoy their responses.

The next section covers the types of sampling.

7. Types of sampling

Now that you know about sample size, here is how to select those samples.

3 methods are covered here: random, stratified, and convenience sampling.

• Random Sampling: When you select your samples randomly from the whole population, it is called random sampling. Random sampling works best for a large target population. The responses it produces represent the whole population well, and selecting random samples takes less time.
• Stratified Sampling: Stratified sampling selects samples from a population that has been categorized. The samples are divided into strata or layers based on factors like age, gender, location, and more. Stratified sampling takes more time.
• Convenience Sampling: Samples are selected from a group that is convenient for the researcher to reach. There is no attempt at random or stratified selection. Convenience sampling works best for exploratory surveys. The samples are easy to collect, and it is a quick way to get initial data.

Test Your Knowledge

Key Takeaways

• The survey sample size is the number of respondents whose opinions are collected to accurately represent the entire targeted population.
• Sample size should be a minimum of 100 and a maximum of 10% of the total population.
• The types of sampling include random, stratified, and convenience sampling.

Keep learning: see how to craft survey questions and browse BlockSurvey's survey templates.

Congratulations! You have completed this lesson.