Continuous Random Variables

Continuous Random Variable

A continuous random variable can assume any continuous value in a given domain.
The probabilities of the continuous range are displayed as a function or a graph.

Probability Density Function (pdf)

A function, 𝑓(𝑥), that describes the probability for a continuous random variable to take on a given
value. The probability is given by the area under the function.

A probability density function is defined when:

(⬚)
𝑓: 𝑅 → 𝑅, 𝑓(𝑥) = 𝑔(𝑥) 𝑓(𝑥) ≥ 0 for 𝑥 ∈ ℝ 𝑓(𝑥) 𝑑𝑥 = 1
⬚

𝑔(𝑥), 𝑎 ≤ 𝑥 ≤ 𝑏
𝑓: 𝑅 → 𝑅, 𝑓(𝑥) = 𝑓(𝑥) 𝑑𝑥 = 1
0, elsewhere
𝑓(𝑥) ≥ 0 for 𝑥 ∈ [𝑎, 𝑏] and 𝑓(𝑥) = 0 for 𝑥 ∈ ℝ ∖ [𝑎, 𝑏]

Example VCAA 2010 Exam 1 Question 7a

The continuous random variable 𝑋 has a distribution with probability density function given by
𝑎𝑥(5 − 𝑥) if 0 ≤ 𝑥 ≤ 5
𝑓(𝑥) = , where 𝑎 is a positive constant.
0 if 𝑥 < 0 or if 𝑥 > 5

The value of 𝑎 will need to make the area under 𝑓 between 0 ≤ 𝑥 ≤ 5 equal 1.
5𝑥 𝑥 5(5) (5) 125 125
𝑎𝑥(5 − 𝑥)𝑑𝑥 = 𝑎 5𝑥 − 𝑥 𝑑𝑥 = 𝑎 ⎯⎯⎯ − ⎯⎯⎯ = 𝑎 ⎯⎯⎯⎯⎯− ⎯⎯⎯⎯ = 𝑎 ⎯⎯⎯ − ⎯⎯⎯ = 1
2 3 2 3 2 3

375𝑎 − 250𝑎 6
⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯⎯= 1 ⇒ 125𝑎 = 6 ⇒ 𝑎 = ⎯⎯⎯
6 125

Calculating Probabilities using Continuous Random Variables

Probabilities are determined by the area under the curve, therefore, the probability of getting exactly a
value (e.g. 5 not 5.0001 or 4.9999) is practically impossible. Therefore, we say it has a probability of 0.
Pr(𝑋 = 𝑎) = 𝑓(𝑥) 𝑑𝑥 = 𝐹(𝑎) − 𝐹(𝑎) = 0

The probabilities can be determined by integration from −∞ or the lower bound to the value.
Since the area under a point is 0, it doesn't matter if the probability is between and including or not
including the value. That is, if the probability uses < or ≤ they will have the same probability.
Pr(𝑋 < 𝑎) = Pr(𝑋 ≤ 𝑎) = 𝑓(𝑥) 𝑑𝑥 , Pr(𝑋 > 𝑎) = Pr(𝑋 ≥ 𝑎) = 𝑓(𝑥) 𝑑𝑥

The probability between two values written as

Pr(𝑎 < 𝑋 < 𝑏) = Pr(𝑎 ≤ 𝑋 < 𝑏) = Pr(𝑎 < 𝑋 ≤ 𝑏) = Pr(𝑎 ≤ 𝑋 ≤ 𝑏) = 𝑓(𝑥) 𝑑𝑥

Since ∫ 𝑓(𝑥) 𝑑𝑥 = ∫ 𝑓(𝑥) 𝑑𝑥 + ∫ 𝑓(𝑥) 𝑑𝑥 we can write the probability beteween the two values as

Pr(𝑎 < 𝑋 < 𝑏) = 𝑓(𝑥) 𝑑𝑥 + 𝑓(𝑥) 𝑑𝑥 = 𝑓(𝑥) 𝑑𝑥 − 𝑓(𝑥) 𝑑𝑥 = Pr(𝑋 < 𝑏) − Pr(𝑋 < 𝑎)

Be Careful
Always check the domain to see if working out the probability is even possible.
If your answer is > 1 or < 0, then some values included are outside of the domain.

Probabilities For Hybrid Functions

Probabilities For Hybrid Functions
Probability density functions for continuous random variables can have 𝑔(𝑥), 𝑎 ≤ 𝑥 ≤ 𝑏
more parts in the hybrid. The probability density function itself does not 𝑓(𝑥) = ℎ(𝑥), 𝑏 < 𝑥 ≤ 𝑐
need to be continuous (it can jump values). 0, elsewhere
To determine the probabilities across domains that include different parts of the hybrid, the integral
must be broken up into separate parts.

Since ∫ 𝑓(𝑥) 𝑑𝑥 = ∫ 𝑓(𝑥) 𝑑𝑥 + ∫ 𝑓(𝑥) 𝑑𝑥 , for 𝑎 < 𝑥 < 𝑏 < 𝑥 < 𝑐, we can write the probability as

Pr(𝑥 < 𝑥 < 𝑥 ) = 𝑓(𝑥) 𝑑𝑥 = 𝑓(𝑥) 𝑑𝑥 + 𝑓(𝑥) 𝑑𝑥 = 𝑔(𝑥) 𝑑𝑥 + ℎ(𝑥) 𝑑𝑥

Otherwise, using a CAS calculator, you can enter a hybrid function and integrate over the whole domain

The total probability (area under the curve) must still be 1.

Pr(𝑎 ≤ 𝑥 ≤ 𝑐) = 𝑔(𝑥)𝑑𝑥 + ℎ(𝑥)𝑑𝑥 = 1

Example VCAA 2011 Exam 2 Question 2 aii ⎧ 0 𝑦<0

In a chocolate factory the material for making each chocolate is ⎪ 𝑦
sent to one of two machines, machine 𝐴 or machine 𝐵. The time, 𝑓(𝑦) = ⎯⎯⎯ 0≤𝑦≤4
⎨ 16
𝑌 seconds, taken to produce a chocolate by machine 𝐵, has the ⎪0.25𝑒 . ( )
𝑦>4
following probability density function. ⎩

𝑦 . ( ) 23 1 .
Pr(3 ≤ 𝑌 ≤ 5) = 𝑓(𝑦)𝑑𝑦 = ⎯⎯⎯𝑑𝑦 + 0.25𝑒 𝑑𝑦 = ⎯⎯⎯− ⎯⎯𝑒 ≈ 0.4155
16 32 2

Calculating Values that Give a Probability

To find a particular value that gives a particular probability, we can solve the equation of the definite
integral and the given probability.

Example VCAA 2006 Exam 1 Question 6b

𝑥
⎯⎯⎯ 1 ≤ 𝑥 ≤ 5
The probability density function of a continuous random variable 𝑋 is given by 𝑓(𝑥) = 12
0 otherwise
5
If Pr(𝑋 ≥ 𝑎) = ⎯⎯, the value of 𝑎 is
8

𝑥 5
⎯⎯⎯𝑑𝑥 = ⎯⎯
12 8

1 𝑥 5
⇒ ⎯⎯⎯ ⎯⎯⎯ = ⎯⎯
12 2 8

1 15
⇒ ⎯⎯ 25 − 𝑎 = ⎯⎯⎯
2 2

⇒ 25 − 𝑎 = 15

⇒ 𝑎 = 10
  ⎯⎯⎯
⇒ 𝑎 = ±√10
  ⎯⎯⎯   ⎯⎯⎯
Since 1 ≤ 𝑥 ≤ 5, then 𝑎 ≠ −√10. Therefore, 𝑎 = √10.