The confidence level is expressed as a percentage and represents how sure you are that the actual percentage of the population who would respond lies within the percentage limit of error. The 95% confidence level means you can be 95% certain; the 99% confidence level means you can be 99% certain. Most researchers use the 95% confidence level. Greater confidence will generate larger sample sizes.

The percentage limit of error is the plus-or-minus error amount or deviation (expressed as a percentage) that you are willing to tolerate from your projected response rate. For example, if you enter a 2% response rate and are willing to accept an error (or deviation) in response of /- .3% (i.e., response between 1.7% and 2.3%) at a confidence level of 95%, your sample size will be 8,366.  Enter the percentage as a whole number and / or decimal (i.e., 10 or .1 for 10%, 1 or .01 for 1%, .001 for .1% of a percent, etc. 

Use this Marketing Campaign Sample Size Calculator (1) to determine a sample size for testing the response to an upcoming B2B or B2C marketing campaign, or for a research survey in which you want to determine how many people to interview or send questionnaires (the minimum sample size). Enter the percentage response rate as a whole number and / or decimal (i.e., 10 for 10%, 1.25 for 1.25%, .5 for .50 % of a percent, etc.)

Use Sample Size Calculator (2) to compute the sample size for a survey or testing depending on the confidence level desired and the confidence interval (also known as margin of error) are known.

Use Finite Universe Sample Size Calculator (3) to compute the sample size for surveying or testing where there is a finite population that can be tested or surveyed.

Use the Confidence Interval (4) Calculator to determine the confidence interval or margin of error when you know the sample size and the population size that is being surveyed or tested.

In the last three calculators, the percentage of population is set to a default value of 50%, but it can be changed to reflect the actual level of accuracy. 50% is a worst case percentage. For example, you might have a population that has a 30% incidence of skin cancer that you are interviewing about cancer treatments, so you should use that as the percentage.

See the definitions panel for explanations of the terms used in the calculators if you aren't sure what they mean.

Confidence Level - The confidence level is expressed as a percentage and represents how sure you are that the actual percentage of the population who would respond lies within the percentage limit of error. The 95% confidence level means you can be 95% certain; the 99% confidence level means you can be 99% certain. Most researchers use the 95% confidence level. Greater confidence will generate larger sample sizes. This calculator is limited to confidence levels of 90, 95 and 99%.

Confidence Interval (Margin of Error) - The confidence interval or the percentage limit of error is the plus-or-minus error amount or deviation (expressed as a percentage) that you are willing to tolerate from your projected response rate, survey or test results. For example, if you enter a 2% response rate and are willing to accept an error (or deviation) in response of 5% (i.e., response between 1.90% and 2.10%) at a confidence level of 95%, your sample size will be75,295. The range of error in these calculators is limited to a maximum of 15%.

Population Size - The population number is how many people are in the group you are surveying or testing, the exact population of people that your sample represents. For example, the number of people living in a city, or the number of people with a given disease.

Percentage - To determine the sample size needed for a given level of accuracy, you must use the worst case percentage of 50%. To determine your level of accuracy, you also need to use this percentage for a sample you already have. The percentage can deviate if you know that among your population there is a greater or lesser incidence of what you are sampling for. For example, you might know that a given disease has an incidence rate of 30% among the total population, in which case, you would enter 30% as the percentage.