What Is a P-Value in Hypothesis Testing?
In inferential statistics, a p-value quantifies the level of statistical evidence against a null hypothesis (H₀). It represents the probability of observing data at least as extreme as your sample findings assuming the null hypothesis is true.
1. Two-Tailed Hypothesis Test (H₁: μ ≠ μ₀)
p=2 × [ 1 − Φ(|z|) ]
2. One-Tailed Directional Tests (Left / Right)
Left Tail: p = Φ(z)|Right Tail: p = 1 − Φ(z)
Step-by-Step Calculation Breakdown (Example: z = 2.10, Two-Tailed Test, α = 0.05)
Step 1: Evaluate Normal Cumulative Distribution Function Φ(|z|)
• For z = 2.10, cumulative probability Φ(2.10) = 0.982136
Step 2: Calculate Single Tail Probability (1 − Φ)
• Upper Tail Area = 1 − 0.982136 = 0.017864
Step 3: Double for Two-Tailed Test and Compare with Alpha
• Two-Tailed p-value = 2 × 0.017864 = 0.035728 (3.57%)
• Since p (0.0357) < α (0.05), we Reject H₀.
Decision Rule Summary
- If p ≤ α: Reject the null hypothesis H₀. The result is statistically significant.
- If p > α: Fail to reject the null hypothesis H₀. There is insufficient evidence of an effect.