Skewed to the right or to the left?

42 Views Asked by At

If a median of some distribution given as a $PDF$ function is larger than its expected value, do we say that the distribution is skewed to the left or to the right?

1

There are 1 best solutions below

0
On

It is not an inmediate implication, but the important idea is that the expected value is very sensitive to outliers. If a distribution has more mass to one side, the opposite tail (less mass, or in other words, less probability that an observation will fall near that range) will pull the mean to that side and we will say the skewness is to that flatter side (that flat tail creates the assimmetry in the distribution). The median will be more stable in relation with extreme values (it is the "center" of the data) so if the mean is more negative than the median, we have a clue that there is some extreme values to the left.