|
-
Oct 3rd, 2006, 05:57 AM
#1
Thread Starter
New Member
Analysis of survey data - Pls help
I have two questions to answer which im struggling with, could anyone pls help? the questions are:
1) In a market research project a local authority has requested the evaluation of the demand for a library. Visitors to the library stay for a mean of 3 hours with a standard deviation of 1.8 hours. Within a sample of 1000 visitors how many can be expected to visit the library for (a) less than 2 hours (b) more than 5 hours (c) between 2 and 5 hours. Assume that the distribution is normally distributed.
2) In order to estimate the percentage of dwellings which have a smoke alarm in the northwest to within 1% for a 95% confidence level a pilot survey was carried out. From a random sample of 30 dwellings, 12 were found to have a smoke alarm installed. How many houses need to be sampled in the main survey?
Thanks!
-
Oct 3rd, 2006, 04:01 PM
#2
Addicted Member
Re: Analysis of survey data - Pls help
Question 1:
Mean = 3; SD = 1.8; n = 1,000
P(x <= 2) = 0.28926 or 1,000 x 0.28926 = 289 visitors
P(x > 5) = 0.13326 or 1,000 x 0.13326 = 133 visitors
P(2 <= x <= 5) = 0.86674 - 0.28926 = 0.57748 or 1,000 x 0.57748 = 578 visitors
Question 2:
p = 12/40 = 40%; e = 0.01; CL = 95%
n0 = Z(a/2).p(1 – p)/e^2 = 1,95996 x 0.4 x (1 – 0.4)/0.01^2 = 9,220
If you know the size N of the population, then:
n = (n0).(N)/[n0 + (N – 1)]
If, for instance N = 1,000, the result would be n = 902 instead.
Last edited by Rassis; Oct 3rd, 2006 at 04:05 PM.
...este projecto dos Deuses que os homens teimam em arruinar...
Posting Permissions
- You may not post new threads
- You may not post replies
- You may not post attachments
- You may not edit your posts
-
Forum Rules
|
Click Here to Expand Forum to Full Width
|