P-value

A p-value < 0.05 means: if H₀ is true, this result has <5% probability

The p-value represents the probability of obtaining results at least as extreme as the observed result, assuming the null hypothesis is true. This means that if the null hypothesis is correct, there is less than a 5% chance of observing such an extreme result purely by random chance.

A very small p-value indicates that the observed outcome is unlikely under the null hypothesis, suggesting that the null hypothesis may not be true. However, it is crucial to remember that a p-value does not measure the probability that the hypothesis is true or the importance of the result.

Misinterpretation of p-values is common, leading to incorrect conclusions about the validity of hypotheses. The American Statistical Association emphasizes that p-values should not be used in isolation and must be considered alongside other evidence and context.

Example

In a study testing the effectiveness of a new drug, a p-value of 0.03 indicates that there is only a 3% chance of observing the observed improvement in patients if the drug had no effect (null hypothesis is true).

Understanding the correct interpretation of p-values helps prevent erroneous conclusions and promotes accurate scientific communication.

Related concepts

Conditional probability

P(A|B) = P(A ∩ B) / P(B)

Expected value

Expected value formula: E[X] = Σ [x * P(x)]

Entropy H = -Σ p(x) log₂ p(x) measures average surprise in bits

Entropy H = -Σ p(x) log₂ p(x) quantifies uncertainty in a system

Logistic regression

Logistic regression probability formula: P(Y=1) = 1 / (1 + exp(-z))

Binomial proportion confidence interval

Binomial proportion confidence interval estimates success probability

Chebyshev's inequality says: P(|X-μ| ≥ kσ) ≤ 1/k²

Chebyshev's inequality states: P(|X-μ| ≥ kσ) ≤ 1/k²

One email a day: 5 concepts + the 5 stories that matter →

Swipe through 100 ML concepts daily

Open TickerNews