The sample means will perhaps be greater or less than µ, but the average of all possible X will be µ -- X is an unbiased estimation of µ.

Median

Order the data from smallest to largest. If there is an odd number of data, then the median is simply the middle value (position (n+1)/2); if there is an even number of data, then it is the average of the two middle values (position n/2 and (n/2)+1.

Quartiles (Q_{1}, Q_{2}, Q_{3})

If the data is ordered from smallest to largest, then as the median has 50% of the data below and it 50% of the data above it, Q_{1} (the first quartile) has 25% of the data at or below it and Q_{3} (the third quartile) has 25% of the data at or above it. For an odd n, then Q_{1} is at the position ( n + 3 ) / 4 and for an even n, then Q_{1} is at the position ( n + 2 ) / 4 and Q_{3} is intuitively at that same position from the largest number (this can be computed as n minus the position of Q_{1}).