The sample size refers to the number of individual pieces of data collected in a survey. It is important in determining the accuracy and reliability of a survey's findings. In order to have sufficient statistical power, besides the population number, you must also think about how much error can be tolerated and how confident you want to be in your results.
The margin of error is the range of values above and below the fragment statistic and is called the margin of error in a confidence interval. The most common values are 1%, 2.5% and 5%. This is the degree of variation that will be present in the results. We can use opinion polls as an example, which often have a margin of error of ±3%. This means that if a survey shows one party winning 58% of the votes, the results could in fact vary by 3% either way, so could actually be between 55% and 61%.
A confidence level refers to the percentage of all possible fragment that can be expected to include the true population parameter. Suppose all possible individuals were selected from the same population, then a 95% confidence level would imply that 95% of the confidence intervals would include the true population parameter.
When deciding on the sampling, you will need to consider both factors, margin of error and confidence interval, and then you can refer to the sample size table to find the individual number you should take.
This guide will teach you:
1. Sample size table
In this table, you will find the exact amount of responses you need based on the confidence level or margin of error.
As you can see from the table, the smaller you want the margin of error to be, the greater the number of responders you should have. The population number increases as you go from 5% margin of error to 1% margin of error. As the confidence level increases and you want to be sure of the responses falling within the given range, you will also need a greater individuals number.
2. Sample size calculator
If we want a 95% confidence interval and a 2.5% margin of error, the calculator tells us that our individuals number should be 377.
If you're looking for ways to increase your survey response rate: take a look at these 34 tips. You'll find this calculator in tip number 8.
Be aware that there are other factors that should also be considered, such as the number of variables you will be analyzing (the greater number of variables, the more individuals you will need) and whether you will be doing quantitative or qualitative research. Gathering qualitative data for a too large fragment may end up being unworkable and unrealistic to analyze, and if you plan to use statistical analysis, a larger sample will allow for more sophisticated statistics to be calculated.
Check out the entire glossary list in a printable list.
- Survey incentives are actually not much different from any other kind of incentive. They are reasons, monetary or non-monetary, physical or emotional that drive or motivate people to fill in your survey. In other words, they would boost survey response rate.
- Survey completion rate: When calculating the survey completion rate, the calculation only takes to account those people who had some interaction with the survey, meaning that they actually started it. We don’t count the number of people who were invited and ignored the invitation.
- Survey Accuracy is the extent to which a survey result represents the attribute being measured in the group of interest or population. Determining how accurate the data captured by a survey reflects the entire population requires computing the confidence interval and the confidence level.