KURT function. The first has a peak at its center; the second is flat. The first is said to be leptokurtic. its kurtosis is positive. The second is platykurtic; its kurtosis is negative.
Negative? Wait a second. How can that be? Kurtosis involves the sum of fourth powers of deviations from the mean. Because four is an even number, even the fourth power of a negative deviation is positive. If you're adding all positive numbers, how can kurtosis ever be negative?
Two histograms, showing two kinds of kurtosis.Here's how. The formula for kurtosis is
where 
is the mean of the scores, N is the number of scores, and s is the standard deviation.
Uh, why 3? The 3 comes into the picture because that's the kurtosis of something special called the standard normal distribution. Technically, statisticians refer to this formula as kurtosis excess — meaning that it shows the kurtosis in a set of scores that's in excess of the standard normal distribution's kurtosis. If you’re about to ask the question “Why is the kurtosis of the standard normal distribution equal to 3?” don't ask.
This is another formula you'll probably never use because Excel's KURT function takes care of business. The image above shows the scores an example, a selected cell, and the Function Arguments dialog box for KURT.
To use KURT:
- Enter your numbers into a worksheet and select a cell for the result. For this example, you enter scores into the first ten rows of columns B, C, D, and E. You elect cell H2 for the result.
- From the Statistical Functions menu, select KURT to open the Function Arguments dialog box for
KURT. - In the Function Arguments dialog box, enter the appropriate values for the arguments. In the Number1 box, enter the array of cells that holds the data. Here, the array is B1:E10. With the data array entered, the Function Arguments dialog box shows the kurtosis, which for this example is negative.
- Click OK to put the result into the selected cell.
Using KURT to calculate kurtosis.