Probability Density Functions
Uploaded by
Catherine WoodrowProbability Density Functions
Uploaded by
Catherine WoodrowL1: Probability Density Functions (PDF)
What are Continuous Random Variables?
Continuous Data is data which can take on an infinite number of outcomes between two intervals.
Examples of continuous random variables include weight and height.
With continuous data we can't really draw a histogram as there would be an 'infinite' number of columns
with 'zero' widths.
Instead we can use a curve.
A probability density function (PDF) is a function satisfying two properties:
A continuous probability distribution is defined to be a probability distribution described by a probability
density function (PDF).
With a continuous probability distribution, we cannot calculate the probability for a single outcome, so
P ( X=x ) =0. Instead, we can only calculate the probability for a range of values such as P ( 4 ≤ X < 8 ) .
SOLUTION:
a)
Time (min) Frequency Relative Frequency
0-<4 6
4-<8 8
8-<12 11
12-<16 4
16-<20 2
20-<24 1
b)
c)
(i) P(X < 12) = ____________________________
(ii) P(X 16) = ___________________ (iii) P( 4 X < 8 ) = ________________________
In the previous example we estimated probabilities of continuous random variables using relative frequency.
However, it is not accurate as decimals are allowed and we cannot possibly record a table for each and every
value that x can take on.
• Instead of using a table and having different entries for x, we can use the real numbers on the x-axis. The y-
axis represents f(x) which is called a probability density function (PDF).
• The probability density function graph is a continuous curve.
• To find a probability of x, we integrate f(x) over an interval and the area under the curve represents the
probability.
• We can only find the probability of a range of values P(a≤ X ≤ b) and not a single outcome so P(X = x ) =0.
As with discrete probability distributions, the SUM OF ALL THE PROBABILITIES MUST BE 1
Examples:
1)
2)
3)