I know that the median value $(\text{Med})$ for a variable $X$ characterised by the contentious PDF function $f_X(x)$ can be calculated by finding $\text{Med}$ in:

$\int^\text{Med}_{-\infty} dF_X(x) = \int^\text{Med}_{-\infty} f_X(x) dx = {1\over2}$

And $F(x)$ is the CDF of $X$. In other-words:

$ \text{Med} = F^{-1}(1/2)$

So if $f_X(x) = {1\over b-a}$, i.e a uniform distribution [a,b] we have that:

$\int^\text{Med}_{a} {1\over b-a} dx = {\text{Med}-a\over b-a} = {1\over2}$


$Med = {1\over2}(b+a)$

The median absolute deviation is given by

$ \text{Mad} = G^{-1}(1/2)$

Where $G$ is the CDF of the |x-M|. How can I find $\text{Mad}$? Is there a similar formula for it?


You can use :

$G(x)=P(|X-M|\leq x)=P(X\in[M-x;M+x])$

Thus, for a uniform distribution, for $x\leq\frac{b-a}{2}$ :


$G(x)=\frac{1}{2}\Leftrightarrow x=\frac{b-a}{4}$


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.