Sometimes we're interest in hypothesis tests about two population means.
The creator of the formula decided it was a good number for calculating and the default calculations stick with it.
This is the p-value for the data set.
It determines whether we need to use the t-distribution or the Z-distribution Next, we must know the hypothesis testing type.
Note: There is no specific reason we use 0,05 p-value for default calculation.
A low p-value means that under the null hypothesis there's little probability that for another sample the test statistic will generate a value at least as extreme as the one as observed for the sample you already have.