Ask your own question, for FREE!
Statistics 16 Online
OpenStudy (anonymous):

Any ideas please? Simple random sample of voters will be taken in a large state. Researchers will construct an approximate 95% confidence interval for the percent of the state’s voters who will vote for Candidate A. Find the minimum sample size needed to ensure that the width of the interval (right end minus left end) is at most 6%. Thank you.

OpenStudy (amistre64):

"an approximate" lends ear to the empirical rule: z = 2

OpenStudy (amistre64):

100 - 6 is 94; not 95 tho .... but still an approxiamtion from the setup:\[CI: p\pm E\] we get \[E = z\sqrt{\frac{pq}{n}}\] solving for n we get \[n = z^2\frac{pq}{E^2}\]

OpenStudy (amistre64):

without knowing anything about the sample data ... thats as fas as i can get with it

OpenStudy (anonymous):

@amistre64 thank you, but what to put for numbers?? Because I have to give a numerical answer!

OpenStudy (amistre64):

You have not given us any numbers to work with. as such, the best guess I would have for p and q is .5 giving us:\[n = 2^2\frac{.25}{E^2}\] I might have been forgetful about the E tho ... thats prolly where we want the 6% to go; a .06 error \[n = 2^2\frac{.25}{.06^2}\] if we want a more accurate resutl we would have to know more about the standard deviation to address the "pq" setup, and we could use a more accurate 95% z value (1.96)

OpenStudy (anonymous):

@amistre64 thank you alot..but it cannon be n= 300...

OpenStudy (amistre64):

OpenStudy (amistre64):

why cant it be close to 300? when i use a more accurate Z value of (1.96) the results are still 267

OpenStudy (anonymous):

@amistre64 because i tried 300 and was wrong. the exercise says: "answer with a positive integer; correct to the nearest 50"

OpenStudy (amistre64):

hmmm, the width of the interval is at most 6% ... we might want to halve that then. use 3% and see how that runs

OpenStudy (anonymous):

@amistre64 i did not undersand. You mean to be 1100?

OpenStudy (amistre64):

1068 ... but yes the Error in the confidence interval seems to be such that it is not more than a .06 span from end to end. E = .03 in that case n = .25*(1.96/.03)^2 would be my best guess

OpenStudy (anonymous):

1068? my calculator says 1067.1 ;p i will try agian later i must leave thank you a lot

OpenStudy (amistre64):

since people are considered not to be divisible .... rnding up to 1068 is perfered

OpenStudy (anonymous):

@amistre64 You are absolutely correct. Thank you!!

Can't find your answer? Make a FREE account and ask your own questions, OR help others and earn volunteer hours!

Join our real-time social learning platform and learn together with your friends!
Can't find your answer? Make a FREE account and ask your own questions, OR help others and earn volunteer hours!

Join our real-time social learning platform and learn together with your friends!