Statistical Significance: Why the P Value Controls False Positives

In hypothesis testing, a finding is declared to be statistically significant if the p value computed from the data is below a predefined significance level (often 5%). In this video we show that this guarantees that the probability of a false positive is bounded by the significance level. In addition, we prove that the distribution of the p value under a simple null hypothesis is uniform (if the test statistic is continuous), which is very useful to understand multiple testing.

Photo by Kenny Eliason on Unsplash

[thefantasticman]

Thank You sir I am searching this topic for hours