Statistical significance is used to determine if the statistics are reliable and if the differences that are found will always be found. The most common type of statistical significance is the t-statistic and the p-value. Very small differences can be significant when the sample size is large. When the sample size is small, then much larger differences are required to achieve statistical significance. To determine how many measurements are needed to find statistical significance, the sample size can be estimated before the study occurs.
- Skill level:
Other People Are Reading
Things you need
- Standard deviation
- Maximum acceptable difference (alpha level)
- Confidence Level
- Calculator or statistics program
Determine the alpha level to be used. This refers to the amount of error that is acceptable in the statistical analysis. Normally an alpha level of 0.05 is used, though this level can be different. The higher the level, the more error exists in the calculation.
Estimate the average mean that you want from the study. Many times this estimated mean is from previously done research. Alternatively it can be calculated from a small test survey or research on a small sample group
Plug the values into this equation:
n = t^2 x p(1-p)/m^2.
t is the confidence level, normally 95 per cent (standard value of 1.96). p is the estimated mean, and m is the margin of error or alpha level. n will be the calculated sample size.
Tips and warnings
- Statistical software will be able to quickly and easily calculate the sample size. Many websites also provide sample size calculators (see Resources).
- 20 of the funniest online reviews ever
- 14 Biggest lies people tell in online dating sites
- Hilarious things Google thinks you're trying to search for