Variation in the distribution of a statistical variable is called the measure of dispersion. The standard deviation of a distribution that consists of an aggregation of averages is called the standard error. A normal distribution contains at least 100 samples. 95 percent confidence limits define the 95 percent confidence interval boundaries. For a normal distribution, the mean of the distribution is between these confidence interval boundaries 95 percent of the time.
Calculate "M," or the mean of the normal distribution, by adding all the data values and dividing them by the total number of data points.
Calculate "SE," or the standard deviation of the normal distribution, by subtracting the average from each data value, squaring the result and taking the average of all the results.
Calculate the 95 percent confidence limits with the formulas M - 1.96SE and M + 1.96SE for the left- and right-hand side confidence limits.
- Photo Credit Jupiterimages/Goodshoot/Getty Images
How to Calculate Margin of Error
The margin of error is a number that represents the accuracy of a poll.
One can determine this amount by using an...
How to Calculate the Confidence Interval of the Mean
The confidence interval of the mean is a statistical term used to describe the range of values in which the true mean...
How to Calculate a Confidence Interval
When analyzing the sample data from an experiment or research study, perhaps one of the most important statistical parameters is the mean:...
How to Calculate Confidence Intervals for a Proportion
In statistics, a confidence interval refers to the range in which there is a specific probability that a certain parameter (e.g., mean)...
How to Calculate Sample Size from a Confidence Interval
When researchers are conducting public opinion polls, they calculate the required sample size based on how precise they want their estimates to...
How to Find Confidence Intervals on a TI-83
When calculating statistical data, it's nearly impossible to leave every stone unturned. Statistics are almost always based on a sample of all...