If your \(x = 542\) (ie the number of “successes” and your \(n = 3611\), this is how you can have R calculate a 90% Confidence Interval for you.
binom.test(x = 542, n = 3611, conf.level = .90)[["conf.int"]]
## [1] 0.1403939 0.1602214
## attr(,"conf.level")
## [1] 0.9
25.
- Point estimate p hat is 417/2306= 0.181
- n is a random sample smaller than 5% of adult Americans aged 18+, and 341.8 is greater than 10.
- (0.168,0.194).
- We are 90% confident that the proportion of adult Americans 18 years+ who have donated blood in the past 2 years is between 0.168 and 0.194.
26.
- Point estimate p hat is 496/1153=0.430
- n is a random sample smaller than 5% of the total population size, and 282.6003> 10.
- (0.401,0.459).
- We are 95% confident that the proportion of workers and retirees in the U.S. 25 years old+ who have less than $10,000 in savings is between 0.401 and 0.459.
27.
- Point estimate p hat is 521/1003= 0.519.
- n is a random sample smaller than 5% of the total population size, and 250.388>10.
- (0.488,0.550) We are 95% confident that the proportion of adult Americans who believe that televisions are a luxury they could do without is between 0.488 and 0.550.
- Yes, it is possible that a supermajority of Americans believe that television is a luxury they could do without because it’s possible it’s not in the confidence interval, although it is unlikely.
- (0.450, 0.512).
28.
- Point estimate p hat is 768/1024= 0.75.
- n is a random sample smaller than 5% of total population size and 192>10.
- (0.715, 0.785) We are 99% confident that the proportion of adult Americans aged 18+ for which the issue of family values is extremely or very important in determining their vote for president is between 0.715 and 0.785.
- It is possible that it is not in the confidence interval, however it is very unlikely.
- (0.215,0.285).
29.
- (0.071,0.151).
- (0.058,0.164).
- The level of confidence increases and the margin of error increase simultaneously.