Scribd Logo
Upload

Welcome to Scribd!

  • 36 views

    The Geometric Distribution

    Uploaded by

    shaw taonameso
    This document discusses the geometric distribution, a special discrete random variable where the number of trials needed for the first successful outcome is modeled. It provides examples of calculating probabilities and expected value and variance for geometric distributions. It also gives conditions for when a situation can be modeled by a geometric distribution and important results about the distribution.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    The Geometric Distribution

    Uploaded by

    shaw taonameso
    36 views5 pages
    This document discusses the geometric distribution, a special discrete random variable where the number of trials needed for the first successful outcome is modeled. It provides examples of calculating probabilities and expected value and variance for geometric distributions. It also gives conditions for when a situation can be modeled by a geometric distribution and important results about the distribution.

    Original Title

    THE GEOMETRIC DISTRIBUTION

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses the geometric distribution, a special discrete random variable where the number of trials needed for the first successful outcome is modeled. It provides examples of calculating probabilities and expected value and variance for geometric distributions. It also gives conditions for when a situation can be modeled by a geometric distribution and important results about the distribution.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    36 views5 pages

    The Geometric Distribution

    Uploaded by

    shaw taonameso
    This document discusses the geometric distribution, a special discrete random variable where the number of trials needed for the first successful outcome is modeled. It provides examples of calculating probabilities and expected value and variance for geometric distributions. It also gives conditions for when a situation can be modeled by a geometric distribution and important results about the distribution.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 5

    1

    STATISTCS TOPIC 3: SPECIAL DISCRETE RANDOM


    VARIABLES
    TUTORIAL 3
    (GEOMETRIC DISTRIBUTION)
    In this topic learners should be able to :

     Draw up probability distribution table relating to a given situation involving a discrete


    random variable X, and calculate E(X) and Var(X)
     Use formulae for probabilities for the binomial and geometric distributions, and recognize
    practical situations where these distributions are suitable models . Use notations 𝑩(𝒏, 𝒑) and
    𝑮𝒆𝒐(𝒑) where 𝑮𝒆𝒐(𝒑) denotes the distribution in which 𝒑𝒓 = 𝒑(𝟏 − 𝒑)𝒓−𝟏 𝒇𝒐𝒓
    𝒓 = 𝟏 , 𝟐 , 𝟑 ,. . .
     Use formulae for expectation and variance of the binomial distribution and for the
    expectation of the geometric distribution (no proofs of formulae)

    Introduction

    In this tutorial, we shall learn about the second and last special discrete random variable which our syllabus
    requires us to study – the Geometric distribution.

    In a Geometric distribution, the discrete random variable, X, is “the number of trials needed to obtain
    the first successful outcome”

    Examples are: “the number of trials needed for a learner driver to pass a driving test at a Vehicle
    Inspection Depot (VID)”,

    OR “the number of times needed to toss a fair die in order to obtain a six”.

    E . NYANDOROH 0772241993
    2

    1 Conditions for a situation to be modelled by a Geometric distribution


    For a situation to be described using a geometric model, conditions to be satisfied

     Independent trials are carried out,


     the outcome of each trial is deemed either a success or failure,
     the probability, 𝑝, of success is the same for each trial.
    The discrete random variable, 𝑋, is the number of trials needed to obtain the first success.

    2 Notations used
    When above conditions are satisfied, we write

    𝑋 ~ 𝐺𝑒𝑜(𝑝)

    We read 𝑋 follows a geometric distribution with probability of success, 𝑝.

    The formula allocating probabilities is given by,

    𝑃(𝑋 = 𝑟) = (1 − 𝑝)𝑟−1 𝑝 , where 1 − 𝑝 is probability of failure and


    𝑟 = 1 ,2 ,3 , . . .

    NB 𝑟 𝑐𝑎𝑛 𝑛𝑜𝑡 𝑡𝑎𝑘𝑒 𝑎 𝑣𝑎𝑙𝑢𝑒 0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒 𝑛𝑜 𝑡𝑟𝑖𝑎𝑙 𝑤𝑖𝑙𝑙 𝑏𝑒 𝑚𝑎𝑑𝑒.

    Example 1

    The random variable 𝑋 is such that 𝑋~𝐺𝑒𝑜( 0.35)

    Find (i) 𝑃(𝑋 = 4)

    (ii) 𝑃(𝑋 > 4)

    (iii) 𝑃(𝑋 ≤ 3)

    State the mode of the distribution.

    Solution

    (i) 𝑃(𝑋 = 4) = (0.65)3 (0.35) = 𝟎. 𝟎𝟗𝟔


    (ii) 𝑃(𝑋 > 4) = 1 − 𝑃(𝑋 = 1) − 𝑃(𝑋 = 2) − 𝑃(𝑋 = 3) − 𝑃(𝑋 = 4)
    = 1 − (0.65)0 (0.35) − (0.65)1 (0.35) − (0.65)2 (0.35) = 𝟎. 𝟏𝟕𝟖

    E . NYANDOROH 0772241993
    3

    (iii) 𝑃(𝑋 ≤ 3) = [𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) + 𝑃(𝑋 = 3)]


    = 0.35 + 0.228 + 0.148
    = 𝟎. 𝟕𝟐𝟔
    For any geometric distribution, the mode is equal to 1, i.e. one attempt is the most likely

    number of trials to get a success.

    Example 2

    Solution

    Notice here that, no fixed trials are made like we had for a binomial. Also we need to deduce the
    1
    probability of success i.e. probability of throwing a six as 6 .

    1
    (i) 𝑋~𝐺𝑒𝑜 (6)

    5 3 1
    𝑃(𝑋 = 4) = (6) (6) = 𝟎. 𝟎𝟗𝟔.

    (ii) 𝑃(𝑋 ≤ 3) = 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) + 𝑃(𝑋 = 3) 𝑂𝑅 1 − 𝑃(𝑛𝑜 𝑠𝑢𝑐𝑐𝑒𝑠𝑠 𝑖𝑛 𝑓𝑖𝑟𝑠𝑡 3 𝑎𝑡𝑡𝑒𝑚𝑝𝑡𝑠)

    = 𝟎. 𝟒𝟐.

    Important results about a geometric distribution:

    For a geometric distribution, 𝑃(𝑋 ≤ 𝑛) = 𝑃(𝑠𝑢𝑐𝑐𝑒𝑠𝑠 𝑖𝑛 𝑛 𝑜𝑟 𝑓𝑒𝑤𝑒𝑟 𝑎𝑡𝑡𝑒𝑚𝑝𝑡𝑠)

    = 1 − 𝑃(𝒏𝒐 𝑠𝑢𝑐𝑐𝑒𝑠𝑠 𝑖𝑛 𝑓𝑖𝑟𝑠𝑡 𝒏 𝑎𝑡𝑡𝑒𝑚𝑝𝑡𝑠)

    That is 𝑃(𝑋 ≤ 3) = 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) + 𝑃(𝑋 = 3) 𝑂𝑅 𝟏 − 𝒒𝟑

    Also 𝑷(𝑿 > 𝒏) = 𝒒𝒏.

    E . NYANDOROH 0772241993
    4

    Example 3

    𝑋 ~ 𝐺𝑒𝑜(𝑝) and 𝑃(𝑋 = 2) = 0.1275. If 𝑝 > 0.5 , find 𝑃(𝑋 > 2). [4]

    Solution

    (1 − 𝑝)𝑝 = 0.1275

    𝑝 − 𝑝2 = 0.1275

    𝑝2 − 𝑝 + 0.1275 = 0 ⟹ 𝑝 = 0.85 𝑜𝑟 0.15

    Therefore 𝑝 = 0.85 and 𝑋 ~ 𝐺𝑒𝑜(0.85)

    Hence 𝑃(𝑋 > 2) = 𝑞 2 ⟹ 𝑃(𝑋 > 2) = (0.15)2 = 𝟎. 𝟎𝟐𝟐𝟓

    3 Expectation, 𝑬(𝑿), and Variance, 𝑽𝒂𝒓(𝑿) for 𝑿~𝑮𝒆𝒐( 𝒑)

    If 𝑋~𝐺𝑒𝑜( 𝑝) then,

    𝟏
    𝑬(𝑿) =
    𝒑
    𝒒
    𝑽𝒂𝒓(𝑿) = , where 𝑞 = 1 − 𝑝.
    𝒑𝟐

    Example 4

    1
    The probability that a learner driver passes his test at a Vehicle Inspection Depot is . A learner driver
    4

    counts the number of attempts, 𝑛, until he/she passes the driving test.

    (i) State a suitable statistical distribution which can be used to model the above situation, [1]

    (ii) Find the mean and variance of the distribution, [3]

    (iii) Find the smallest value of 𝑛, for which there is a probability of at least 0.7 that the learner

    driver will need only 𝑛 or fewer trials to pass the driving test. [4]

    E . NYANDOROH 0772241993
    5

    Solution

    𝟏
    (i) 𝑿~𝑮𝒆𝒐 (𝟒)
    3
    1 𝑞 4
    (ii) 𝐸(𝑋) = 𝑝 = 𝟒 and 𝑉𝑎𝑟(𝑋) = 𝑝2 = 1 2
    = 𝟏𝟐
    ( )
    4

    (iii) Given 𝑃(𝑋 ≤ 𝑛) ≥ 0.7


    𝑃(𝑋 ≤ 𝑛) = 1 − 𝑞 𝑛 ≥ 0.7 from important deductions.
    3 𝑛
    1 − (4) ≥ 0.7
    3 𝑛
    1 − 0.7 ≥ (4)

    0.3 ≥ 0.75𝑛 . Critical value is 𝑛 = 4.1 after taking logarithms both sides
    Try 𝑛 = 4 and 𝑛 = 5 in above inequality, hence smallest value of 𝒏 = 𝟓.

    END OF TOPIC

    E . NYANDOROH 0772241993

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy