Mathematical Statistics (MA212M)

Lecture Slides
Lecture 6
Discrete Random Variable

Def: [Discrete RV] A random variable is said to have discrete

distribution if there exists an atmost
Xcountable set SX ⊂ R such that
P(X = x) > 0 for all x ∈ SX and P(X = x) = 1. SX is called
x∈SX
the support of X .
Def: Define a function fX : R → [0, 1] by
(
P(X = x) if x ∈ SX
fX (x) =
0 otherwise .

The function fX is called the probability mass function of X .

Example 1, X is discrete, Example 2, X is discrete, Example 3, X1 is
not discrete, but X2 is discrete.
Remarks

◮ For a discrete random variable X ,

X
FX (x) = fX (y ).
y ∈SX
y ≤x

◮ For a discrete random variable X ,

fX (x) = FX (x) − FX (x−).

Properties of PMF

P
1 fX (x) ≥ 0 for all x ∈ R. 2
x∈SX fX (x) = 1.

Theorem: Suppose a real valued function h : R → R satisfies the

following conditions:
1 h(x) ≥ 0 for all x ∈ R. D = {x : h(x) > 0} is atmost countable.
P
x∈D h(x) = 1.
2

Then h(·) is a probability mass function of some discrete random

variable.
Example

1 (Bernoulli Distribution) X ∼ Bernoulli (p): SX = {0, 1},

fX (0) = 1 − p, fX (1) = p.
2 (Binomial Distribution) X ∼ Bin(n , p): SX = {0, 1, . . . , n},
n

k n−k
fX (k) = k p (1 − p) .
3 (Geometric Distribution) X ∼ Geo(p): SX = {0, 1, . . .},
fX (k) = p(1 − p)k .
4 (Poisson Distribution) X ∼ Poi (λ) (λ > 0): SX = {0, 1, . . .},
−λ k
fX (k) = e k!λ .
Application

Example 31: Suppose that an airplane engine will fail, when in flight,
with probability 1 − p independently from engine to engine. The
airplane will make a successful flight if at least 50 percent of its
engines remain operating. For what values of p is a four engine plane
preferable to a two engine plane? (Ans: p > 2/3)