Results 1 to 6 of 6

Math Help - Binomial Distributions

  1. #1
    Newbie
    Joined
    Mar 2010
    Posts
    13

    Binomial Distributions

    Supposing that an interviewer needs to interview five people and that the probability that each person agrees to be be interviewed is 0.6, what is the expected value and variance of the number of people she must ask to interview five people? The answers are E = 8.33 and V = 5.56.

    My textbook isn't very clear on how to calculate expected values and variance - can someone push me in the right direction?
    Follow Math Help Forum on Facebook and Google+

  2. #2
    MHF Contributor
    Joined
    Aug 2007
    From
    USA
    Posts
    3,110
    Thanks
    2
    My textbook isn't very clear on how to calculate expected values and variance - can someone push me in the right direction?
    I'd be pretty close to stunned if this actually were the case. I can believe the text maybe isn't talking to you very well. No all books speak to everyone. No worries.

    Quote Originally Posted by mintsharpie View Post
    Supposing that an interviewer needs to interview five people and that the probability that each person agrees to be be interviewed is 0.6, what is the expected value and variance of the number of people she must ask to interview five people? The answers are E = 8.33 and V = 5.56.
    For a binomial distribution with p = 0.6 and n trials, we have ALWAYS,

    E[X] = n*p

    Var(x) = n*p*q

    Where q = 1 - p

    That's it. Is that in your book? It had better be, otherwise, why is the author published?

    So.

    n*(3/5) = 5 ==> n = 5 / (3/5) = 25/3

    You tell me about the variance. I hardly can wait to see how the book's answer was created. Maybe I'm not understanding the question.
    Follow Math Help Forum on Facebook and Google+

  3. #3
    Flow Master
    mr fantastic's Avatar
    Joined
    Dec 2007
    From
    Zeitgeist
    Posts
    16,948
    Thanks
    5
    Quote Originally Posted by TKHunny View Post
    I'd be pretty close to stunned if this actually were the case. I can believe the text maybe isn't talking to you very well. No all books speak to everyone. No worries.



    For a binomial distribution with p = 0.6 and n trials, we have ALWAYS,

    E[X] = n*p

    Var(x) = n*p*q

    Where q = 1 - p

    That's it. Is that in your book? It had better be, otherwise, why is the author published?

    So.

    n*(3/5) = 5 ==> n = 5 / (3/5) = 25/3

    You tell me about the variance. I hardly can wait to see how the book's answer was created. Maybe I'm not understanding the question.
    I know your answer agrees with the book and I know it appears that the question has come from the section of the book dealing with binomial distribution, but I disagree that it's a binomial distribution question.

    From the wording of the question, my understanding is that

    Quote Originally Posted by Wikipedia
    ... there is a sequence of independent Bernoulli trials, each trial having two potential outcomes called “success” and “failure”. In each trial the probability of success is p and of failure is 1 − p. We are observing this sequence until a predefined number r of failures has occurred.
    For my money, technically this question requires the negative binomial distribution: Negative binomial distribution - Wikipedia, the free encyclopedia

    where X is the random variable "number of successes (number of people who do NOT want to be interviewd)", p = 0.4 (the 'failures' are the people who want to be interviewed and so success is a person who does not want to be interviewed) and r = 5 (stop after five 'failures' are observed).

    Then Mean = E(X + 5) = E(X) + 5 = (20/6) + 5.
    Follow Math Help Forum on Facebook and Google+

  4. #4
    MHF Contributor
    Joined
    Aug 2007
    From
    USA
    Posts
    3,110
    Thanks
    2
    Agreed. I was uncomfortable working the Binomial Distribution backwards, but failed to challenge the original premise. Perhaps this explains the variance?
    Follow Math Help Forum on Facebook and Google+

  5. #5
    Newbie
    Joined
    Mar 2010
    Posts
    13
    Quote Originally Posted by TKHunny View Post
    For a binomial distribution with p = 0.6 and n trials, we have ALWAYS,

    E[X] = n*p

    Var(x) = n*p*q

    Where q = 1 - p

    That's it. Is that in your book? It had better be, otherwise, why is the author published?

    So.

    n*(3/5) = 5 ==> n = 5 / (3/5) = 25/3

    You tell me about the variance. I hardly can wait to see how the book's answer was created. Maybe I'm not understanding the question.
    If E(X) = n*p, wouldn't that make the answer 5 x 0.6, which is 3? I don't understand where the 8.33 is coming from - where did you get the 25 from in order to divide it by 3?

    All my book says is that  E(X) = \sum p(x) (there's supposed to be a y under the sum symbol, but I don't know how to do that). Then there's a lot of steps to follow, and at the end, it ends up being  E(X) = \lambda . It's not very clear, I have no idea what it's talking about. I took an advanced probability class in grade 12, and the textbook was really clear and I actually understood most of it, but this year I'm completely lost. I know it's university so it's supposed to be harder, but it just seems like the textbook moves too quickly and includes limited examples, so I'm confused most of the time.

    Quote Originally Posted by mr fantastic View Post
    For my money, technically this question requires the negative binomial distribution: Negative binomial distribution - Wikipedia, the free encyclopedia

    where X is the random variable "number of successes (number of people who do NOT want to be interviewd)", p = 0.4 (the 'failures' are the people who want to be interviewed and so success is a person who does not want to be interviewed) and r = 5 (stop after five 'failures' are observed).

    Then Mean = E(X + 5) = E(X) + 5 = (20/6) + 5.
    I'm sorry, I don't understand. Where did the 20 and the 6 come from?
    Follow Math Help Forum on Facebook and Google+

  6. #6
    Flow Master
    mr fantastic's Avatar
    Joined
    Dec 2007
    From
    Zeitgeist
    Posts
    16,948
    Thanks
    5
    Quote Originally Posted by mintsharpie View Post
    If E(X) = n*p, wouldn't that make the answer 5 x 0.6, which is 3? Mr F says: It's not Binomial, forget that idea. It's negative binomial, as I said in my earlier post.
    I don't understand where the 8.33 is coming from - where did you get the 25 from in order to divide it by 3?

    All my book says is that  E(X) = \sum p(x) (there's supposed to be a y under the sum symbol, but I don't know how to do that). Then there's a lot of steps to follow, and at the end, it ends up being  E(X) = \lambda . It's not very clear, I have no idea what it's talking about. I took an advanced probability class in grade 12, and the textbook was really clear and I actually understood most of it, but this year I'm completely lost. I know it's university so it's supposed to be harder, but it just seems like the textbook moves too quickly and includes limited examples, so I'm confused most of the time.



    I'm sorry, I don't understand. Where did the 20 and the 6 come from?
    Go to the link I gave, read the formula for mean, substiute the given values (as defined by me in my earlier post).
    Follow Math Help Forum on Facebook and Google+

Similar Math Help Forum Discussions

  1. Replies: 3
    Last Post: July 15th 2010, 05:33 AM
  2. Binomial Distributions Question
    Posted in the Statistics Forum
    Replies: 3
    Last Post: April 17th 2010, 05:18 PM
  3. Normal and binomial distributions
    Posted in the Statistics Forum
    Replies: 2
    Last Post: July 28th 2009, 02:50 PM
  4. Probability in binomial distributions
    Posted in the Statistics Forum
    Replies: 1
    Last Post: May 31st 2009, 08:22 PM
  5. Binomial & Poisson Distributions
    Posted in the Advanced Statistics Forum
    Replies: 12
    Last Post: September 16th 2008, 01:27 AM

Search Tags


/mathhelpforum @mathhelpforum