Definition of Confidence Interval:
- A confidence interval gives an estimated range of values, calculated from a given set of sample data, which is likely to include an unknown populatio parameter.
- Confidence intervals are usually calculated at 95 percent, but they can be set to any percentage level. It is expected that when intervals are calculated for a group of samples from the same population then a certain percentage (or confidence level) will include the unknown population parameter.
- Confidence intervals are often calculated using a program such as Excel or Minitab.
- The width of the confidence interval indicates some level of uncertainty regarding the unknown parameter; the wider the interval, the less certainty.
- You can learn more with a confidence interval than a hypothesis test as you work with a range of possible values rather than a definitive “reject” or “don’t reject” of H0.