This is the probability that the selected interval (confidence interval includes the true value of the variable. Example. If you select 95, it means that if we repeat the survey 100 times we would expect the answer to any question to vary between the chosen margin of error in 95 out of 100 times.
This is the percentage of people who give a particular answer to a question in a survey. If 98% of people select an answer there is no much room for error. However, if 45 or 55% select a particular answer, we don’t have a clear majority and the chance for error gets bigger. We often can’t anticipate how people will answer, so use 50% as you worse case scenario, which will cover most cases when estimating sample size. If you are lucky to have previous research then use it as a guideline to estimate the percentage that would yield the highest accuracy. Note. Enter an integer in this box. No decimals or percentage sign.
You may or may not know the size of the total population for the target sample you are studying. If you don’t know and can assume it to be large (over 20,000) leaving blank). However, smaller population sizes would have an impact on the sample you will need.
This is the percentage you see quoted in the media (e.g.+/-3%) when poll numbers are discussed. This percentage defines the lower and upper bounds of the confidence interval. Here we indicate how much error we can live with and try to ensure that our sample estimate doesn’t differ from the true population by more than this percentage a certain number of times (confidence level). Imagine you want to know how many people like chocolate, then you may want a sample that ensures that the percentage of people saying they like chocolate in your survey doesn’t differ more than, say, 3% from the true percentage of these people in the population, 95% of the time (confidence level). Note. Enter an integer in this box for the Sample Calculator. No decimals or percentage sign.