Paper 6. Probability density functions and their properties, finding probabilities, the mean, the variance and the median by integration.
Written for the 2026–2027 syllabus · 4 min read
6.3 Continuous random variables
Probability density functions
A continuous random variable can take any value in a range. Its probability density function (pdf), f(x), describes it, and an area under the graph gives a probability.
f(x) itself is not a probability, and it can be larger than 1. For a single value, P(X=a)=0, so P(X<a) and P(X≤a) are the same.
Finding a constant
∫03kx2dx=[3kx3]03=9k=1⇒k=91
Finding probabilities
∫019x2dx=[27x3]01=271
Mean and variance
E(X)=∫039x3dx=[36x4]03=49
∫039x4dx=[45x5]03=527
Var(X)=527−(49)2=0.3375
The median and percentiles
The median m splits the area in half.
[27x3]0m=21⇒m3=13.5⇒m=2.38
The same method gives any percentile. The 90th percentile uses an area of 0.9 from the bottom.
Infinite ranges
A pdf can run to infinity. The upper limit is handled by seeing what the term tends to as x grows.
∫1∞kx−4dx=[−3x3k]1∞=0+3k=1⇒k=3
E(X)=∫1∞3x−3dx=[−2x23]1∞=23
∫1∞3x−2dx=[−x3]1∞=3⇒Var(X)=3−49=43
Sketching a pdf
The graph must be zero outside the stated range, so show it at zero there or stop at the limits.
Label the limits on the x-axis, and any height that the function gives at those ends.
The graph may jump to zero at the ends of its range, as f(x)=91x2 does at x=3.
Reading the shape
Fact
How to use it
Symmetric pdf
The mean and median are on the line of symmetry
The peak of the pdf
This is the mode
Most of the area is on the left, with a long tail to the right
Mean is greater than median
Most of the area is on the right, with a long tail to the left