Identify the hypothesis type (one-sample, two-sample, paired, correlation/regression, chi-square, etc.)
Choose the significance test and corresponding test statistic (z, t, chi-square, F, etc.)
Collect the data and compute the sample statistics needed for the test
Compute the test statistic using the correct formula for the chosen test
Determine the degrees of freedom (if applicable)
Compute the p-value from the test statistic using:
A p-value table (by matching the statistic and degrees of freedom)
Software (R, Python, Excel, calculator) with the appropriate function
The cumulative distribution function (CDF) of the test’s distribution
Select the correct tail:
Left-tailed: p-value = P(Test statistic ≤ observed)
Right-tailed: p-value = P(Test statistic ≥ observed)
Two-tailed: p-value = 2 × min(P(Test statistic ≤ observed), P(Test statistic ≥ observed))
Report the p-value as the probability under the null hypothesis of observing a result at least as extreme as the one obtained
Compare the p-value to the chosen significance level α to make a decision (reject or fail to reject)