The cumulative distribution function (CDF) gives the cumulative probability associated with a distribution. Specifically, it gives the area under the probability density function, up to the value you specify. Use the CDF to determine the probability of a response being lower than a certain value, higher than a certain value, or between two values.

For example, soda can fill weights follow a normal distribution with a mean of 12 ounces and a standard deviation of 0.25 ounces. The probability density function (PDF) describes the likelihood of each possible value of fill weight. The cumulative distribution function gives the cumulative probability for each value along the PDF.

Use the CDF to determine the probability that a randomly chosen can of soda will have a fill weight less than 11.5 ounces, greater than 12.5 ounces, or between 11.5 and 12.5 ounces.

In order to calculate a p-value, you must first calculate the cumulative distribution function (cdf). The p-value is 1 – cdf.

Suppose you perform a multiple linear regression analysis with the following degrees of freedom: DF (Regression) = 3; DF (Error) = 2; and the F-statistic = 4.86.

- Choose .
- Choose Cumulative probability.
- In Numerator degrees of freedom, enter
`3`. - In Denominator degrees of freedom, enter
`2`. - Choose Input constant and enter
`4.86`. - In Optional storage, enter
`K1`. Click OK. K1 contains the cumulative distribution function.

- Choose .
- In Store result in variable, enter
`P-value`. - In Expression, enter
`1-K1`. Click OK.

The calculated p-value, as shown in the Data window, is 0.175369. Using the 0.05 cutoff value, you would not conclude statistical significance since 0.175369 is not less than 0.05.
###### Note

This example is for an F-distribution; however, you can use a similar method for other distributions.