EDA M3S1

DISCRETE PROBABILITY DISTRIBUTION REQUIRED CONDITIONS for DISCRETE

PROBABILITY FUNCTION ARE:
A random variable
- is a function that associates a real number with p(x) ≥ 0 FOR ALL VALUES OF x
each element in the sample space. A random
variable is a variable whose values are determined
by chance.
∑p(x)=1
We shall use a capital letter, say X, to denote a FORMULA
random variable and its corresponding small letter,
x in this case, for one of its values. p(x)=___n!___
Random Variable x!(n-x)!
- Is a numerical description of the outcome of
an experiment

2 TYPES OF RANDOM VARIABLE px(1-p)n-x

 Discrete Random Variable
- may assume either a finite number values DISCRETE UNIFORM PROBABILITY DISTRIBUTION
or an infinite sequence of values - is the simplest example of a discrete
Example: probability distribution given by a formula.
1. Number of Sales - THE DISCRETE UNIFORM PROBABILIY
2. Number of Calls FUNCTION IS:
3. People in Line
4. Mistakes per Page f(x)=1/n
the values of the RANDOM VARIABLE are equally likely
 Continuous Random Variable
where: n = is the number of values the random variable
- may assume any numerical value in an
may assume.
interval or collection of intervals
Example: ______________________________________________
1. Length
2. Depth SUMMARY MEASURES
3. Volume 1. Expected Value
4. Time - Mean of the Probability Distribution
5. Weight - Weighted Average of all possible values
__________________________________________ µ=E(x)=∑x p(x)
2. Variance
DISCRETE PROBABILITY DISTRIBUTIONS - Weighted average of squared deviation about
- The probability distribution for a variable the mean
describes how probabilities are distributed
over the values of the random variable.
∂2=E[(x-µ)2]=∑(x-µ)2p(x)
3. Standard Deviation
- D.P.D. can be described with the use of
table, graph or equation ∂=√∂2
SUMMARY MESAURES CALCULATION TABLE
PROBABILITY DISTRIBUTION x p(x) xp(x) x-µ (x-µ)2 (x-µ)2p(x)
- is defined by the probability function,
denoted by p(x) which provides the
probability for each value of the random total ∑xp(x ∑(x-µ)2p(x)
variable. )
PROBABILITY RULES FOR DISCRETE BINOMIAL PROBABILITY
RANDOM VARIABLES Characteristics of a Binomial Experiment:
- Let x be a discrete random variable 1. The experiment consists of
with probability distribution p(x) n identical trials
mean µ 2. Only two possible outcomes on each
standard deviation ∂ trial (S-Success/ F-Failure)
then, depending on the shape of p(x), 3. The p of S remains the same –from
the following probability statements trial to trial
can be made: p of S = p
Chebyshev’s – Empirical p of F = q
P(x-∂< x < µ+∂) ≥0 – ≈0.68
P(x-2∂< x < µ+2∂) ≥3/4 – ≈0.95 NOTE THAT q = 1 – p
P(x-3∂< x < µ+3∂) ≥8/9 – ≈1.00 4. The trials are independent
5. The binomial random variable x is the
number of S’s in n trials
n x n− x n!
p(x)= p q = p x (1− p)n− x
x x ! ( n−x ) !
EDA M3S2
p(x) = probability of x ‘successes’
BINOMIAL and POISSON DISTRIBUTION
p = probability of a ‘success’ on a single trial

Binomial Distribution q=1-p

n = number of trials
- Frequency distribution of the number
x = number of ‘successes’ in n trials
of ‘successes’ in a sample of (x= 0, 1, 2, 3…..n)
n observations (trials) n-x = number of ‘failures’ in n trials
2 Possible Outcome (of an Experiment)
- Success FORMULAs
- Failure
E(x) = µ = np
Example: Var(x) = ∂2 = npq; q=1-p
1. Number of reds in 15 spins of roulette
wheel S.D. = ∂ = √(npq)
2. Number of defective items in a batch
of 5 items
3. Number of customers who purchase
out of 100 customers who enter store NOTE: p=1
(each customer is equally likely to
purchase)
POISSON DISTRIBUTION
- a discrete probability distribution
- useful when n is LARGE and p is SMALL
- and when the independent variables occur
over a period of time
- can be used when a density of items is
distributed over a given area/volume
EXAMPLES:
Number of plants growing per acre
Number of defects in a given length
of videotape

FORMULA
P(x;) = e-x
x!
where:
x = 0, 1, 2, 3, …..
e= 2.7183….

FORMULA
= np
nCr= pr(1-p)n-r

EDA M3S1

CONTINUOUS PROBABILITY DISTRIBUTION

UNIFORM PROBABILITY DISTRIBUTION - Most important distribution for continuous
random variables
- Widely used for making statistical
f(x)= { 1/(b-a), 0) inferences in both:
Natural Sciences
where a≤x≤b Social Sciences

EXAMPLE:
- Height of people
- Scientific Measurements
- Test Scores
- Amounts of Rainfall
PROBABILITY AS AN AREA

1
In a graph; f(x) =
2 2
−(x−µ) −2 ∂
e
∂ √(2 π )
µ = mean
- horizontal = x ∂ = standard deviation
- vertical = f(x) Π = 3.1416
E =2.71828

CHARACTERISTICS:
so:
- Symmetric – Bell-shaped

Normal Probability Distribution is defined by

=P(_≤x≤_) - Mean (m)
o Negative
=Area o Positive
=f(x)*x o Zero
- Standard deviation (s) – width of the curve
o larger values (WIDER)
o flatter values (STEEPER)
- high s = wider; lower
UNIFORM CONTINUOS DISTRIBUTION
- low s = steeper; higher
- EXPECTED VALUE
- VARIANCE
Highest Point on NORMAL CURVE
a+b - Mean
E(x) = 2 - Median
- Mode
Probability for N.R. Variable are given by:
(b−a)2 - areas under the curve
2
Var(x) = ∂ = 12 - 1 total area(.5 for both left and right)

STANDARD NORMAL DISTRIBUTION

NORMAL PROBABILITY DISTRIBUTION
 - is a normal distribution with the special
properties
mean = µ = 0
S.D. = ∂ = 1
2
−z /2

y= e
√ (2 π )

NOTE:
- Normally distributed variables can be
transformed into the standard normally
distributed variable
value−mean
z= standard deviation ¿
¿

z= X−µ
∂

z– used to designate the standard normal

random variable

RELATIONSHIP BETWEEN THE POISSON AND

CUMULATIVE PROBABILITY EXPONENTIAL DISTRIBUTIONS
- Probability that z≤ 1 is the area under the
curve to the left of 1

EXPONENTIAL DISTRIBUTION
Density Function:

CUMULATIVE PROBABILITIES Exponential Distribution

- the continuous random variable y has the

exponential distribution with constant rate
parameter v if