Binomial Distribution

The binomial distribution is a discrete distribution displaying data that has only TWO OUTCOMES and each trial includes replacement.

Such as:

  • PASS / FAIL
  • GO / NO-GO
  • SUCCESS / FAILURE
  • IN / OUT
  • HOT / COLD
  • MALE / FEMALE
  • DEFECTIVE / NOT DEFECTIVE
  • RIGHT-HANDED / LEFT-HANDED
  • HIGH / LOW
  • HEADS / TAILS

Assumptions

  1. Each trial has only two outcomes
  2. The experiment has n identical trials
  3. Each trial is independent of the other trials
  4. The probability of getting one outcome (success) p is held constant and the probability of getting the other outcome (failure) is also held constant, represented by (1 - p).
  5. Includes replacement for each trial. It can be used to approximate without replacement trials but it is suggested to use hypergeometric distribution formulas.

    Let's evaluate the assumptions:

    A coin flip is an example of two outcomes and each flip has the same chance for both outcomes (meaning independent). Flipping the coin n amount of times means there are n identical and independent trials. Nothing changes from one flip to another and the odds are the same for each flip.
Binomial Distribution Central Tendencies

The following formula is used to compute the number of experimental outcomes resulting from x successes in n trials.

Binomial Experimental Outcomes

For example: 4! (4 factorial) = 4*3*2*1 = 24

The Binomial Distribution Probability Function is shown below:

Binomial Probability Function

Example One

A manufacturing process creates 3.4% defective parts. A sample of 10 parts from the production process is selected. What is the probability that the sample contains exactly 3 defective parts?

SOLUTION:
There are two outcomes: Defective / Not-Defective, therefore the Binomial Distribution equation is applied.

p = 0.034
n = 10
then q = 1-p = 1 - 0.034 = 0.966 (96.6%)
Need the probability that x = 3.

Substitute the values into the Binomial Probability Function and solve:

Example One of applying the Binomial Distribution

Example Two

Forty-five percent of all registered voters in a national election are female. A random sample of 8 voters is selected. The probability that the sample contains 2 males is:

SOLUTION:
55% are male and there are two outcomes: MALE / FEMALE
n = 8
p = 0.55 (55%)
q = 1-p = 0.45
Need the probability that x = 2

Example Two of applying the Binomial Distribution

Example Three

79% percent of the students of a large class passed the final exam. A random sample of 4 students are selected to be analyzed by the school. What is the probability that the sample contains fewer than 2 students that passed the exam?

There are two outcomes: PASS / FAIL

p = 0.79
n = 4

Solving for the probability that x < 2.

Note that we need to compute p(x<2). So, it is necessary to add the P(x=0) to the P(x=1).

Each P(x=0) and P(x=1) must be calculated separately and added.

p(x<2) = p(x=0) + p(x=1)

Substitute the following values into the Binomial equation to find p(x=0):

n = 4
p = 0.79
q = 1 - p = 1 - 0.79 = 0.21
x = 0

PLUS

n = 4
p = 0.79
q = 1 - p = 1 - 0.79 = 0.21
x = 1

Example Three of applying the Binomial Distribution

There is 3.12% chance of selecting fewer than 2 students that passed the exam when randomly selecting 4 students when 79% of them passed.

There are also Binomial tables that can be used when the input variables are known (and found within the table).


Application of the Binomial Distribution







Return to BASIC STATISTICS

Return to SPC Charts

See other Discrete Distributions

Search current job openings related to Six Sigma

Return to the Six-Sigma-Material Home Page



 Site Membership
CLICK HERE


Six Sigma Green Belt Certification
Black Belt Certification

Six Sigma

Templates & Calculators


Six Sigma Modules

The following presentations are available to download.

Click Here

Green Belt Program (1,000+ Slides)

Basic Statistics

SPC

Process Mapping

Capability Studies

MSA

Cause & Effect Matrix

FMEA

Multivariate Analysis

Central Limit Theorem

Confidence Intervals

Hypothesis Testing

T Tests

1-Way Anova Test

Chi-Square Test

Correlation and Regression

SMED

Control Plan

Kaizen

Error Proofing


Advanced Statistics
in Excel

Advanced Statistics in Excel

Six Sigma & Lean Courses

Agile & Scrum Online Course