p-values

🙋‍♀️ Does anyone know what a p-value is? And why do we always choose 0.05?

Statistics~2 min read

p-value

The probability of observing your data (or something more extreme) if the null hypothesis were true.

More formally, if we have a null hypothesis H₀ and we observe some test statistic T, then:

Where t is the observed value of our test statistic.

Interactive p-value Simulation

Interactive Parameters

1030100

Number of observations in the sample

The hypothesized population mean under H₀

The actual population mean for data generation

The threshold for statistical significance

python

Interactive Plot:

💡 Try: hover over elements, zoom with mouse wheel, pan by dragging, use toolbar buttons

Common Misconceptions

p-values are frequently misunderstood. Let's clarify some common misconceptions:

p-value is the probability that the null hypothesis is true

The p-value is calculated assuming the null hypothesis IS true. It cannot tell us the probability that it's true.

A smaller p-value means a larger effect

p-values depend on both effect size AND sample size. A tiny effect with huge sample size can have a very small p-value.

p-value measures evidence against the null hypothesis

Smaller p-values provide stronger evidence that our data is inconsistent with the null hypothesis.

Mathematical Foundation

For a one-sample t-test, we calculate the t-statistic as:

Where:

  • is the sample mean
  • μ₀ is the hypothesized population mean
  • s is the sample standard deviation
  • n is the sample size

The p-value is then calculated using the t-distribution with n-1 degrees of freedom:

The factor of 2 accounts for the two-tailed test (we care about differences in either direction).

Key Takeaways

  • → p-values measure evidence against the null hypothesis
  • → They depend on both effect size and sample size
  • → Statistical significance ≠ practical significance
  • → Always interpret p-values in context
  • → Consider complementary measures like confidence intervals
Published on June 27, 2025