In statististics if we have the finite number of set and the probability of the set is called Discrete probability distribution. For an example for a cars on a road, deaths by cancer, tosses until a die shows a first 6. If we measure anything it is called as continuous probability distribution function. For an example we can to say the electric voltage, rainfall, and hardness of steel. In both cases we can determined the distribution by the following distribution function
F(x) = P(X ≤ x)
This is the probability that X will assume any value not exceeding x.
Continuous random variables and probability distribution:
Discrete random variables appear in experiments which is having finite set (defectives in a production, days of sun shines in Chicago, customers standing in a line etc.). Continuous random variables is appear in the experiments which we can't count but we can measure (length of screws, voltage in a power etc.). If we are find the the value probability for the continuous variable then it is called continuous probability distribution. By the definition of a random variable of X and its for the distribution are of continuous type will be defined as the following integral.
F(x) = `int_-oo^xf(v)dv`
it is called density of the distribution, is non negative, and is continuous perhaps except for finitely many x-values.
The continuous random variables are simpler than the discrete ones with respect to intervals. Indeed in the continuous case the continuous probability distribution of the four probabilities corresponding to a < X ≤ b, a < X < b, a ≤ X < b, a ≤ X ≤ b with any fixed a and b (> a) are all same.
Sample problem for probability distribution:
Continuous probability distribution problem 1:
Let X have the density function f(x) = .75(1 - x2) if -1 ≤ x ≤ 1 and zero otherwise. Find the value of distribution function. Find the continuous probability distribution of P(-1/2 ≤ X ≤ 1/2). Find x such that P(X ≤ x) = 0.95.
Solution:
F(x) = `int_-1^x`(1 - v2) dv= 0.5 + 0.75 x2 -.25x3 if -1 ≤ x ≤ 1,
And F(x) = 1 if x > 1
P(-1/2 ≤ x ≤ 1/2) = F(1/2) - F(-1/2) = `int_(-1/2)^(1/2)`(0.5 + 0.75 x2 -.25x3) dx = 68.75%
Because for continuous probability distribution P(-1/2 ≤ x ≤ 1/2) = P(-1/2 < x ≤ 1/2)
Continuous probability distribution P(X = x) = F(x) = 0.5 + 0.75x -1.25x3 = 0.95
If we solve this we will get x = 0.73