In all likelihood, you have used a Likert scale (or something you’ve called a Likert scale) in a survey before. It might surprise you to learn that Likert scales are a very specific format and what you have been calling Likert may not be. Not to worry — researchers that have been doing surveys for… Read More »
Sample Size – How many completed surveys do I need?
We get this question all of the time, and while the real answer is: 'it depends', the good news is, the larger the population size, the lower your sample size has to be to be confident you're receiving the best information. Your Sample Size is the number of people you should be getting completed surveys from.
As you can see from the list below, the larger the population size is, the difference in the sample size that you need becomes smaller and smaller.
So for example, right now, to draw conclusions about our SurveyGizmo customers, we can poll a select number of our customers in order to find out about the entire population. However, if we wanted to draw conclusions about all marketers worldwide (not limited to just our customers) only surveying our customers would lead to bias, and we would need to have a larger sample size.
Can you help us determine our sample size?
Most definitely! We can help you determine your sample size based on your desired confidence level, margin of error and total population size.
First off, your confidence level tells you how sure you can be about the information provided by your existing. It is expressed in the form of a percentage, and reflects the amount of time that you want the true outcome to fall within the margin of error (confidence interval). The standard for most studies is 95%. This means you can be 95% certain that your sample size reflects your total population.
The margin of error (confidence interval), expressed as a +/- percent, gives a range for which actual results should fall within. The smaller the margin of error, the more confidence one should have that survey results are accurate for the total population. The standard for most studies is +/-5%
Population size is the total number of people from whom you are sampling responses.
You can reference the included table to see the number of responses that are recommended based on the total population size of your target audience.
| Population Size | Recommended Sample Size |
|---|---|
| 10 | 10 |
| 100 | 80 |
| 200 | 132 |
| 300 | 169 |
| 400 | 197 |
| 500 | 218 |
| 600 | 235 |
| 700 | 249 |
| 800 | 260 |
| 900 | 270 |
| 1,000 | 278 |
| 2,000 | 323 |
| 3,000 | 341 |
| 4,000 | 351 |
| 5,000 | 357 |
| 10,000 | 370 |
| 20,000 | 377 |
| 100,000 | 383 |
| 100,000,000 | 384 |
About: The recommended sample size is based on a 95% confidence level and +/-5% margin of error
For example, you own an ice cream shop and you want to survey your customers. If you have 500 customers (population size) and you want a confidence level of 95% and a margin of error of +/-5%, for an accurate survey you would want to get 218 completed responses (sample size) from your ice cream shop customers.
Even with such a high Population Size, why is the sample size no more than 400?
Research has found that having a sample size of more than 400 people (no matter what your population size is) will not provide you any more accurate information than if you had more. Why survey more people than you need to?
If you'd like to learn more about sample size and other best practices for great survey design, you're welcome to check out our Great Survey Design courses that we offer every few weeks. To learn more, please visit: Great Survey Design Courses
Happy Surveying Everyone!
Have questions? Want to comment on this? Join the discussion on our SurveyGizmo Support site.
Apr. 17 
Apr. 5