0
   

Chi Squared test

 
 
Reply Sat 9 Jun, 2012 02:10 am
A mathematics test of 100 multiple- choice questions is to be given to all freshmen entering a large university. Initially, in a pilot study the test was given to a random sample of 20 freshmen. Suppose that, for the population of all entering freshmen, the distribution of the number of correct answers would be normal with a variance of 250.
a. What is the probability that the sample variance would be less than 100?
b. What is the probability that the sample variance would be more than 500?
  • Topic Stats
  • Top Replies
  • Link to this Topic
Type: Question • Score: 0 • Views: 3,457 • Replies: 3
No top replies

 
JPB
 
  1  
Reply Sat 9 Jun, 2012 07:05 am
@raghav674,
Why are you looking to do a chi square on normally distributed data?
0 Replies
 
rdalt131
 
  1  
Reply Thu 25 Oct, 2012 05:29 pm
@raghav674,
a) 19*100/250 = 7.6 (see chi table) = P(s^2<100) = (1 - p = 1 - .99) = .01
b) 19*500/250 = 38 (see chi table) = P(s^2>500) = (1 - p = 1 - .995) = .005

to answer the other guy about normal distribution:
"The chi-square distribution and the resulting computed probabilities for various values of s^2 require that the population distribution be normal."
Statistics - Newbold, 7th edition, pg. 272
houdaa
 
  0  
Reply Fri 24 Sep, 2021 12:30 am
@rdalt131,
to @raghav674,
you write see chi table (consider the second question b)==> I look into the table and try to find the 38 value? I found many: 37.916 (almost 38, for alpha 0.10), 38.885 (for the alhap=0.05) and 38.932 (for alpha0.01) so which one is the right one? and what the df=19 has to do here?
Thank you in advance
0 Replies
 
 

Related Topics

 
  1. Forums
  2. » Chi Squared test
Copyright © 2022 MadLab, LLC :: Terms of Service :: Privacy Policy :: Page generated in 0.03 seconds on 07/01/2022 at 04:13:32