Binomial Distribution
Table of Contents
1. Binomial Probability Distribution
1.1. characteristics
Binomial -> 2 outocmes {Success or Fail}
n trials
independent trials
Same Probabilty of success throughotu the trial
1.2. A common practice/guidline
/Sampling without replacement from a large population:
(trials can be considered independent as long as the sample size is less than 10% of the population size.)/
n < 10% of N
[1 million 90% soccer]
take one from this and the probability of the first is 900,000/1,000,000 1st person
take another from this and the probability is 899,999/1,000,000 ~ .8999 ~ .9 2nd person
1.3. Example 1
Two electronic components are selected from the production line of 100 such components for thorough inspection. It is known that 90% of the components are “good”. Find the probability that the two inspected components are “good”.
2 outcomes (good or bad)
n = 2
2/100 = 2%<10% -> independant
p = .9%
Binomial [x]
Probability of both being good
P(both good)
A = 1st good B = 2nd good
P(AnB) = P(A)*P(B|A)
(.9)(.9) = .81
technically it is (.9)(.89) = .8091
but because its binomial we can assume independance!
1.4. Example 2
At 25oC, 80% of a certain type of laser diodes have efficiency above 0.3 mW/mA. For five diodes, selected by simple random sampling from a large population of such diodes, find the probability of the following events.
Success = S = efficiency above .3…
Failure = F = efficiency below .3…
n = 5
5 from a large population so lets assume its less than 10%
let X = {# successes}
p = .8 in each trial
Binomial [x]
find probability of..
all five have efficiency above .3 at 25C
.85 = .32768
So, P(X = 5) = .328
only the second diode selected has efficiency below .3 at 25C
–> SFSSS
Cant have P(x= 4) because F can be anyware
(.2)*(.84) = .08192
Exactly one of the five diodes has effiency below .3 at 25C
–> e.g. FSSSS, SFSSS, … , 5 total
5*(.2)*(.84)
So, P(x = 4) = .4096
exactly two of the five diodes have effiency below .3 at 25C
–> e.g. FSFSS, SFFSS, P1P2 = P2P1 (Order does not matter)
(5*4)/2! = 10 ways
10*.22*.83 = .2048
1.5. Example 3
Suppose 70% of all purchases in a certain store are made with credit card. Let X denote the number of credit card uses in the next 10 purchases. (Suppose there is a large population of purchases made at this store.)
S = {credit, no credit}
x = (# of credit card uses)
n = 10 purchases
P = .7
Assume independance because large population
Binomial [x]
Find P(5 ≤ X ≤ 8).
p(x=5) + p(x=6) + p(x=7) + p(x=8)
P(x=5)
SSSSSFFFFF -> .75 * .35
(10 choose 5) * .75 * .35
P(x=6)
SSSSSSFFFF -> .76 * .34
(10 choose 6) * .76 * .34
P(x=7)
SSSSSSSFFF -> .77 * .33
(10 choose 7) * .77 * .33
P(x=8)
SSSSSSSFFF -> .78 * .32
(10 choose 8) * .78 * .32
Equation
Σ r = 5 to 8 (10 choose r) .7r*3(10-r)