My Math Forum need help with a statistics probability problem

 Probability and Statistics Basic Probability and Statistics Math Forum

 November 13th, 2007, 10:45 PM #1 Newbie   Joined: Nov 2007 Posts: 2 Thanks: 0 need help with a statistics probability problem I am looking at a sample of an infinite population of manufactured parts. The population is a normal distribution (whatever that means in this case, since I don't know the standard deviation) and 5% of the parts are known to be defective. Now my question: 5% of the manufactured parts of the infinite population are defective. Calculate the probability that the sample of 400 parts contains 36 or more defective parts. How do I do this?
 November 14th, 2007, 04:37 AM #2 Global Moderator     Joined: Nov 2006 From: UTC -5 Posts: 16,046 Thanks: 938 Math Focus: Number theory, computational mathematics, combinatorics, FOM, symbolic logic, TCS, algorithms You could do it combinatorially. The chance that exactly n parts out of 400 are defective is .95^(400-n) * .05^n * (400 choose n), then sum this formula from 0 to 35 and subtract from 1. This is a use of the binomial formula, though it requires big numbers: 400 choose 35 is 24685184473786479717864752464078290163400663996640 0. But you were asked to use the normal distribution, which is a great approximation for the binomial distribution at large numbers. The mean is easy to find, and the standard deviation for a binomial distribution is sqrt(np(1-p)) = sqrt(400 * 0.05 * 0.95). So use a z-table with those parameters.
 November 14th, 2007, 02:07 PM #3 Newbie   Joined: Nov 2007 Posts: 2 Thanks: 0 You know, I think I posted this is the wrong section, because this is a college level statistics course and I have been dealing with sampling distributions of sample means and t-scores and the like. I think I'm supposed to use some of that stuff.
November 14th, 2007, 06:17 PM   #4
Global Moderator

Joined: Nov 2006
From: UTC -5

Posts: 16,046
Thanks: 938

Math Focus: Number theory, computational mathematics, combinatorics, FOM, symbolic logic, TCS, algorithms
Quote:
 Originally Posted by euromath You know, I think I posted this is the wrong section, because this is a college level statistics course and I have been dealing with sampling distributions of sample means and t-scores and the like. I think I'm supposed to use some of that stuff.
Yeah, probably. Of course if it looked like a high school problem I probably wouldn't have answered it.

 Tags probability, problem, statistics

 Thread Tools Display Modes Linear Mode

 Similar Threads Thread Thread Starter Forum Replies Last Post Mighty Mouse Jr Probability and Statistics 2 February 4th, 2013 07:23 AM Deeper Advanced Statistics 12 September 11th, 2011 10:42 AM MasterOfDisaster Probability and Statistics 4 August 11th, 2011 10:49 PM kylerwoods Probability and Statistics 1 May 21st, 2010 04:34 AM katielangford1 Advanced Statistics 0 December 31st, 1969 04:00 PM

 Contact - Home - Forums - Cryptocurrency Forum - Top