The probability density of the normal distribution is : $$ f(x) = \frac{1}{\sqrt{2\pi}\sigma} \cdot e^{-\frac{1}{2}(\frac{x-\mu}{\sigma})^2}$$

And for a random variable $X$ such that : $X \sim \mathcal N (0, 1)$ then we have : $$f(x) = \frac{1}{\sqrt{2\pi}} \cdot e^{-\frac{1}{2}x^2}$$

Yet what is the intuition behind this formula ? Why is there the number $\pi$ and $e$ in the formula of the probability density of the normal distribution ?

Moreover, in a lot of my exercices on the normal distribution it's always saying at the beginning of the exercice :

Let $X$ be a random variable that follow a normal distribution.

Yet, how can we know that a random variable follows a normal distribution ? For example let's say we are studying some process, and more spefically the behaviour of a random variable. Then how can we know, and from which properties of this random variable we can say that it follows a normal distribution ?

  • $\begingroup$ The number $\pi$ is there just to make sure that you have a valid probability function. The number $e$ can be viewed as the result of taking limit of some probability function, for example if the sample size in binominal distribution goes to infinity, its limiting probability is a normal pdf. Central Limit Theorem is probably the most important reason why normal distribution is so ubiquitous. It also has a lot of nice properties and is convenient for the computational (thus pedagogical) purpose. $\endgroup$
    – SiXUlm
    Commented May 19, 2017 at 21:15
  • 1
    $\begingroup$ Does this answer your question? Intuition behind Normal distribution forumula $\endgroup$
    – Lu4
    Commented Mar 25 at 0:51

2 Answers 2


Robert's answer is good! And I'll provide an intuition about how we arrive at this distribution (your first question):

We could view normal distribution is the limit case of a binomial distribution as sample size $N$ goes to $\infty$


One reason that random variables are often (approximately) normal is because of the Central Limit Theorem. Essentially, a random quantity is likely to have approximately a normal distribution if its deviations from the average are relatively small and are the cumulative result of many independent influences, each of which is very small.


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .