When you calculate a statistic the result is not going to be perfectly accurate because of random errors in your observations. You therefore can give the result as one value along with a confidence interval (CI) around it.
There are two interpretations of a CI. One interpretation is that you can be confident, with the stated level of confidence, that the true value of your statistic lies within the CI.
The other interpretation is that if you repeated your experiment then, for the stated percentage of cases, the statistic would lie within the CI.
Confidence intervals may be calculated for any statistics, but the most common statistics for which CI's are computed are mean, proportion and standard deviation. I have include a link, which contains a worked out example for the confidence interval of a mean.
The parameters of the underlying distribution, plus the standard error of observation.
Why confidence interval is useful
You probably mean the confidence interval. When you construct a confidence interval it has a percentage coverage that is based on assumptions about the population distribution. If the population distribution is skewed there is reason to believe that (a) the statistics upon which the interval are based (namely the mean and standard deviation) might well be biased, and (b) the confidence interval will not accurately cover the population value as accurately or symmetrically as expected.
The confidence interval becomes smaller.
Confidence intervals may be calculated for any statistics, but the most common statistics for which CI's are computed are mean, proportion and standard deviation. I have include a link, which contains a worked out example for the confidence interval of a mean.
The parameters of the underlying distribution, plus the standard error of observation.
The confidence interval consists of a central value and a margin of error around that value. If it is an X% confidence interval then there is a X% probability that the true value of the statistic in question lies inside the interval. Another way of looking at it is that if you took repeated samples and calculated the test statistic each time, you should expect X% of the test statistics to fall within the confidence interval.
The Confidence Interval is a particular type of measurement that estimates a population's parameter. Usually, a confidence interval correlates with a percentage. The certain percentage represents how many of the same type of sample will include the true mean. Therefore, we would be a certain percent confident that the interval contains the true mean.
Why confidence interval is useful
The confidence interval becomes wider.
You probably mean the confidence interval. When you construct a confidence interval it has a percentage coverage that is based on assumptions about the population distribution. If the population distribution is skewed there is reason to believe that (a) the statistics upon which the interval are based (namely the mean and standard deviation) might well be biased, and (b) the confidence interval will not accurately cover the population value as accurately or symmetrically as expected.
how are alpha and confidence interval related
No. The width of the confidence interval depends on the confidence level. The width of the confidence interval increases as the degree of confidence demanded from the statistical test increases.
The confidence interval is not directly related to the mean.
The confidence interval becomes smaller.
No, it is not. A 99% confidence interval would be wider. Best regards, NS