Study Notes for Chapter on Binomial Probability Distribution and Related Topics

Chapter Overview

• Title: The Binomial Probability Distribution and Related Topics

• Focus on discrete distributions including the geometric and Poisson distributions.

Section Objectives

• Understand how to compute probabilities using the geometric distribution for first successes.

• Learn to compute occurrences of events utilizing the Poisson distribution.

• Explore the approximation of the binomial distribution when trials are large and success probability is small using the Poisson distribution.

Geometric Distribution

• Definition: The geometric distribution models the number of trials until the first success occurs in a series of identical and independent Bernoulli trials.

Key Concepts

• Binomial Trials vs. Geometric Trials:

  • In a binomial distribution example, one might consider the number of heads from a fixed number of coin flips.

  • In contrast, a geometric distribution instead focuses on how many tosses it takes until the first head appears.

Probability Formula

• For a geometric distribution, if:

  • n = number of the trial on which the first success occurs (i.e., n = 1, 2, 3, …)

  • p = probability of success on each trial, which must remain constant.

• Formula for Probability of Success on the nth Trial:
  $P(n) = p(1 - p)^{n-1}$

Mean and Standard Deviation

• Derived from properties of infinite series:

  • Mean (μ):
    $ext{Mean } ext{μ} = rac{1}{p}$

  • Standard Deviation (σ):
    $ext{Standard deviation } s = rac{ ext{sqrt{1-p}}}{p}$

Example Calculation

• Scenario: For a weighted coin with a probability of heads, p = 0.4, calculate several probabilities:

  1. The probability of the first heads on the 3rd toss:
     $P(3) = 0.4(1-0.4)^{3-1} = 0.4 imes (0.6)^2 = 0.144$

  2. The probability of the first heads on the 5th toss:
     $P(5) = 0.4(1-0.4)^{4} = 0.4 imes (0.6)^{4} ext{ which approximates to } 0.0518$

  3. The probability that at least two tosses are needed for the first heads:
     $P(n ≥ 2) = 1 - P(n=1) = 1 - (0.4 imes (0.6)^0) = 1 - 0.4 = 0.6$

Activity: Assembly Robot Example

• Scenario: An automobile assembly robot has a success rate of 85% (p = 0.85) in locating a weld point on an assembly line.

Probability Queries

1. The probability the robot succeeds in n = 1, 2, or 3 attempts consists of using the standard geometric probability formula: Results:

   • For n=1:
     $P(1) = 0.85$

   • For n=2:
     $P(2) = 0.85(0.15) = 0.1275$

   • For n=3:
     $P(3) = 0.85(0.15)^{2} ext{ which approximates to } 0.0191$

   • Cumulatively, P(1 or 2 or 3) is approximately 99.66%.

2. The probability that the robot will fail all three attempts (complement of the previous probability):

   • Probability of failure after three attempts:
     $1 - 0.9966 = 0.0034$

3. Estimated expectational outcomes if 10,000 panels are processed:

   • Expected failures:
     $10,000 imes 0.0034 = 34 ext{ defective panels}$

Poisson Distribution

• Definition: The Poisson distribution models the number of events occurring in a fixed interval if the events occur independently at a constant rate.

• Use Cases:

  • Number of customers arriving at a café during a time period.

  • Number of phone calls received at a call center in an hour.

Properties of Poisson Distribution

• Notably defined by its mean rate ($ ext{λ}$).

• If a random variable follows a Poisson distribution, define as: $X ext{~ Poisson(λ)}$

  • Probability function:
    $P(r) = rac{λ^{r} e^{-λ}}{r!}$

Mean and Standard Deviation

• Mean:
  $ext{μ} = λ$

• Standard Deviation:
  $s = ext{sqrt{λ}}$

Example Scenario

• Situation: A sandwich shop has an average of 8 customers every five minutes.

• Question: Calculate the probabilities for various customer entries using the Poisson model

  1. For r=3:
     $P(3) = rac{8^{3} e^{-8}}{3!}$

  • Result: 0.0286

  1. For r=6:
     $P(6) = rac{8^{6} e^{-8}}{6!}$

  • Result: 0.1221

  1. For at least one customer:
     $P(r ext{≥} 1) = 1 - P(r = 0) = 1 - e^{-8} ext{ which approximates to } 0.9997$

  2. For r=3 in one minute, adjust λ accordingly:
     $ext{New λ} = rac{8}{5} = 1.6 ext{ corresponding to one-minute averages.}$

  • Result: 0.0998

Poisson Approximation to the Binomial

• The Poisson distribution can approximate the binomial distribution when:

  • The number of trials n is large (≥ 100).

  • The mean number of successes λ = np is small (< 10).

• This approximation is useful for simplifying calculations when dealing with large numbers of trials and low success probabilities.

Example: INFJ Personality Type

• Scenario: An analysis of personality traits in a graduating class of 167 students where the probability of having type INFJ = 2.1%.

• Part a: Validate the Poisson approximation (n=167 and λ=3.5).

• Part b: Determine the probability for occurrences of 0, 1, 2, 3, or 4 INFJs using the Poisson probability function.

• Part c: Estimate the probability for 5 or more INFJ types.

Activity Exercises

• Based on the earlier examples, exercise queries can deepen understanding of the geometric and Poisson distributions, encouraging practical application of concepts learned throughout the chapter.