Optimal sample size
Insights on the importance of choosing an optimal sample size for surveys, determining the margin of error for the results, and a tool for calculating them.
Surveys gather representative data about various variables or statements within a specific target group or population. However, practical constraints such as cost, time, and size often make it unfeasible to survey the entire population. In such cases, it is more practical to use a sample: a selection of respondents that best represent the total population.
Choosing the correct sample size is crucial. An overly large sample can lead to unnecessary expenditure of resources, while a sample that's too small may yield results that lack statistical significance, undermining the reliability of your conclusions.
There are various methods for determining a sample. The commonly used random sample gives all population members equal selection chances. To conduct a random sample survey, determine the
Sample size — the number of responses necessary to achieve results with a high degree of confidence that the responses represent the population.
Number of invitations — The count of surveys requests to send out to achieve the sample size.
Achieved margin of error — the actual margin of error based confidence level and actual number of responses received.
There are various methods for determining a sample. The commonly used random sample gives all population members equal selection chances. To assist you in determining a random sample size, use this tool:
Sample size
Calculating a sample size requires an understanding of these parameters:
Size of the population — Size of the group that is to be represented by the sample. For an employee survey, for example, the population is the total count of employees. Note that the necessary sample size does not change much for population sizes exceeding 20,000.
Preferred margin of error — The margin of error indicates the frequency that individual results do not match those of the population. For example, if 40% of the respondents pick a certain answer and your margin of error is 2%, it means that if you query the total population, you can be sure that between 38% and 42% would pick the same answer. The smaller the allowed margin of error, the larger your sample size will have to be.
Desired confidence level — The confidence level indicates the certainty of the margin of error: how often the actual population's choice for a specific answer is within the margin of error. In market research, margins of error are calculated generally for a confidence level of 95%. This means the survey results will be in line with reality 19 out of 20 times. If you want a higher confidence level (e.g., 99%), your sample will have to be larger.
Number of invitations
Once you have calculated the sample size, you must estimate the ERROR - unresolved reference (glossary-response-rate): how many individuals out of the population to ask to participate to insure the required number of respondents. For example, if you send out email invitations and your sample size is 100 and the expected response rate is 20%, then you will have to send out 500 invitations.
Actual margin of error
After the data-collection phase of your survey, you will know the actual number of respondents that have participated. Unless it happens to be the exact sample size you were looking for, you will then need to calculate the achieved margin of error.
The confidence level and margin of error calculated by our tool is for a random sample. Furthermore, it assumes the response pattern you receive is normally distributed. For sample sizes above 30, the normal distribution usually will be a good estimation of the actual way the responses are distributed (see also the central limit theorem). For smaller sample sizes, the Student's t-distribution is more appropriate but is not supported by our sample size calculator.
