How does JMP calculate p-values?

[#1]

What is the underlying equation/algorithm that JMP uses when it calculates p-value?

[#2 · Accepted solution]

The p-value is the probability of a quantile in some distribution. One uses the cumulative distribution function (CDF) for the distribution model (e.g., normal distribution) to obtain the probability for a given quantile (e.g., data value or sample statistic). The CDF is the definite integral from negative infinity to the quantile x of the distribution probability density function (PDF). How these quantiles are used depends on the question and the distribution.

You can use the probability functions in a column formula or in a script window. For example, the lower one-tailed p-value for a t quantile of -3 with a sample size of 10 is:

t Distribution( -3, 9 )

0.00747818195520711

For example, the p-value for the F quantile of 4 used in a one-way ANOVA for testing the mean of 3 groups, each with 8 observations is:

1 - F Distribution( 4, 2, 21 )

0.0337383327150672

I hope that this information helps. I can't say more without more details about your question. Why do you want to know the 'equation/algorithm?' How will you use this information?