Confidence Interval vs Confidence Levels
In Example 1, it was determined that the researcher, Angus Reid Public Opinion, was fairly sure that the percentage of all hockey fans that feel fights are not important to hockey is between 62.5% and 71.5%. 'fairly sure' is not a very clear statement? what does 'fairly sure' mean in statistics? To clarify this many reports will include a confidence level with their margin of error to define exactly how sure the researcher is. Consider the following excerpt.
The 19 times out of 20 stated at the end of the report is the confidence level. This means if you took many different random samples and determined the confidence interval, 19 times out of 20, or 95% of the time, the confidence interval would contain the true value, which is usually unknown. A 95% confidence interval is common, but other values, such as a 90% confidence interval, can also be used.
A 95% confidence interval and an 80% confidence interval were calculated for 20 samples from the same population. The results are shown in the following diagrams.
Note: These 95% confidence intervals were determined using twenty samples of the same size from the same population. 19 of 20, or 95%, of these confidence intervals include the true value.
Note: These 80% confidence intervals were determined using the same samples as the 95% intervals. Notice that the confidence intervals are narrower than the 95% confidence intervals and that 16 of 20, or 80%, of them include the true value.
| Confidence Interval vs. Confidence Levels | |
|---|---|
| Confidence Interval | Confidence Levels |
|
|
.