In a survey of 250 voters prior to an election 40 indicated
In a survey of 250 voters prior to an election, 40% indicated that they would vote for the incumbent
 candidate.
 a) [4] Estimate with a 90% confidence interval the population proportion of voters who support the
 incumbent.
 b) [4] Using the sample estimate of p from the above study, how large a sample is necessary to
 estimate the proportion of voters who favour the incumbent to within 0.04 with 90%
 confidence?
 c) [4] Repeat (b) assuming that no previous study has been conducted.
Solution
Sample size = 250
Sample proportion for voting incumbent candidate = 40%
Margin of error = -5.1, 5.1
Confidence interval for 90%
= (34.9, 45.1)
-------------------------------------------------------------------------
b) Margin of error =0.04
Margin of error = std error/rt n where n is the sample size.
i.e. Sample size >3206570
-------------------------------------------------------------------------
c) If 40% is not given then we take p =0.5 or 50%
Margin of error =0.04
means sample size <= 3350000
![In a survey of 250 voters prior to an election, 40% indicated that they would vote for the incumbent candidate. a) [4] Estimate with a 90% confidence interval t In a survey of 250 voters prior to an election, 40% indicated that they would vote for the incumbent candidate. a) [4] Estimate with a 90% confidence interval t](/WebImages/19/in-a-survey-of-250-voters-prior-to-an-election-40-indicated-1039093-1761539501-0.webp)
