Slide the observed test statistic onto the null (standard Normal) curve. Pick a tail direction to match your alternative hypothesis. The shaded area is the P-value — the chance of a result at least this extreme if H0 were true. Compare it to α.
Alternative hypothesis (tail)
Significance level (α)
Try: z = 1.96, right tail, α = 0.05 → P ≈ 0.025, reject. Switch to two-sided: P jumps to ≈ 0.050, right on the boundary (P = α is NOT < α). Set z = −2.58, left tail → P ≈ 0.005.