Running a customer survey and not sure how big your sample size should be? Our calculator will show you the minimum sample size you need based on your desired level of precision.
To calculate how many responses you need for feedback polls or surveys, enter the values for the population size, confidence level, and margin of error into the calculator.
Your suggested sample size is:
Now that you know your ideal sample size,
start creating your own Polls and Surveys!
The calculator helps you determine the number of people you need to survey (your sample size calculation)
1. Population size
Population size is the total number of people in the audience you want to study. For example, if you want to use an on-page survey to study your website visitors, and you have 500,000 unique visitors per month, enter “500000” as your population size.
2. Confidence level
Confidence level determines how certain you can be of your results. The industry standard for market research is a 95% confidence level, which means that if you ran the experiment 20 times, you’d get the same results (within a certain margin of error) 19 times.
3. Margin of error
For example, let’s say you asked your users a simple “yes or no” question, and 80% answered “yes” (the question itself doesn’t matter). If you had a margin of error of 5%, with a confidence level of 95%, then running this experiment 20 times would mean that 75% - 85% would answer “yes” in approximately 19 out of 20 experiments.
Lower limit: 80% - 5% = 75%
Upper limit: 80% + 5% = 85%
Don’t know your numbers?
If you don’t know your numbers, you can submit the form using industry standards. These default figures appear in the calculator when you load the page (Population size: 20000, Confidence rate: 95%, Margin of error: +/-5%).
No random sampling is a perfect representation of an entire population, but you can get close. The following factors can impact accuracy, and understanding them will help you create better surveys.
If your population size is small, you’ll need to sample a much larger percentage of your population. As the following chart shows, once your population is large enough, boosting your sample size does little (or nothing) to increase accuracy.
*Accuracy = 95% confidence rate w/5% margin of error.
If your questions discourage certain segments from responding, you’ve got a built-in non-response bias. For example, if you ask clients whether they’ve ever downloaded movies illegally, the “yes” crowd may be less likely to respond for obvious reasons—and that skews your data.
Selection errors occur when you sample people outside the demographic you want to study (e.g., you want to study all your website visitors, but you only collect feedback from your paying customers).
Sampling errors occur when a certain demographic is overrepresented in your sample (e.g., you have a 50-50 mix of men and women, but for whatever reason, more women respond).
The following three principles will help you get some solid data.
Collecting accurate survey data can help you better understand your users and improve your products and messaging in a variety of ways.
Market research is any set of techniques used to better understand a company’s target market. Companies use market research to adapt their products and messaging to market demand. When gathering market research data, use the calculator to achieve a large enough sample size.
Customer satisfaction surveys can help identify areas for improvement. That said,
Net Promoter Score
Net Promoter Score (NPS) is a popular way to measure customer loyalty, ranging from -100 to 100 (the higher the number, the more they love you).
Sending surveys to your customers after they’ve made a purchase, asking how you’re doing and what you can improve, will give you a good sense of how to hold onto good customers and how to win new ones.