+ Reply to Thread
Results 1 to 6 of 6

Thread: Chebyshev's theorem and empirical rule

  1. #1
    Points: 2,762, Level: 32
    Level completed: 8%, Points required for next Level: 138

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Chebyshev's theorem and empirical rule



    can someone please explain how to do this problem? I am so confused!

    Assume the distribution of weights of US adults are normally distributed with mean = 162 lbs and standard deviation= 23 lbs. Find the following probability P (127.5 <x > 196.5) using chebyshev's theorem.

    THank you!!

  2. #2
    Super Moderator
    Points: 8,567, Level: 62
    Level completed: 39%, Points required for next Level: 183
    Dragan's Avatar
    Location
    Illinois, US
    Posts
    1,724
    Thanks
    0
    Thanked 127 Times in 113 Posts
    Quote Originally Posted by vintageglam09 View Post
    can someone please explain how to do this problem? I am so confused!

    Assume the distribution of weights of US adults are normally distributed with mean = 162 lbs and standard deviation= 23 lbs. Find the following probability P (127.5 <x > 196.5) using chebyshev's theorem.

    THank you!!


    Prob{127.5 <x > 196.5} = 0.5555555... using chebyshev's theorem...yawn.

  3. #3
    Points: 4,393, Level: 42
    Level completed: 22%, Points required for next Level: 157

    Posts
    55
    Thanks
    0
    Thanked 0 Times in 0 Posts
    You can not find the actual value of probability using chebyshev's theorem, because it is an inequality. It will give only an upper bound or lower bound of a probability.

  4. #4
    Super Moderator
    Points: 8,567, Level: 62
    Level completed: 39%, Points required for next Level: 183
    Dragan's Avatar
    Location
    Illinois, US
    Posts
    1,724
    Thanks
    0
    Thanked 127 Times in 113 Posts
    Oh darn...The question implies what fraction of the set of measurements (weights) lie between -1.5 and +1.5 standard deviatons of the mean. Using Chebyshev's theorem the answer is:

    at least 1-1/k^2 = 1 - 1/(1.5)^2 = 0.5555...

    Now how's that?


    Just an added follow-up note: Why would someone want to use Chebyshev's theorem if it is known that the underlying distribution is normal?
    Last edited by Dragan; 12-09-2008 at 11:48 AM.

  5. #5
    Points: 4,393, Level: 42
    Level completed: 22%, Points required for next Level: 157

    Posts
    55
    Thanks
    0
    Thanked 0 Times in 0 Posts
    The answer is at least 0.55, which means 0.55 is the lower bound of the probability.

    Chebyshev's theorem is usually using only if the distribution of the random variable is unknown.

  6. #6
    Super Moderator
    Points: 8,567, Level: 62
    Level completed: 39%, Points required for next Level: 183
    Dragan's Avatar
    Location
    Illinois, US
    Posts
    1,724
    Thanks
    0
    Thanked 127 Times in 113 Posts

    Yep, my thoughts too. It looks like someone put together two different questions. Obviously, the probability can be easily computed using the unit normal distribution.

+ Reply to Thread

Similar Threads

  1. Homework help (the empirical rule)??
    By ksinclair in forum Statistics
    Replies: 1
    Last Post: 10-30-2010, 01:22 AM
  2. Empirical Rule question
    By kaboom786 in forum Statistics
    Replies: 1
    Last Post: 10-06-2010, 02:41 PM
  3. help understanding the empirical rule
    By lkasse in forum Statistics
    Replies: 0
    Last Post: 01-18-2008, 03:18 PM
  4. Chebyshev's Theorem and Empirical Rule
    By squeze@hotmail.com in forum Psychology Statistics
    Replies: 1
    Last Post: 09-23-2006, 06:04 AM
  5. Help - questions re: Empirical Rule/Chebyshev
    By skhan in forum Statistics
    Replies: 5
    Last Post: 05-08-2006, 08:34 AM

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts








Advertise on Talk Stats