In: Statistics and Probability
A simple random sample of size n is drawn from a population that is normally distributed. The sample mean, x overbar, is found to be 110, and the sample standard deviation, s, is found to be 10. (a) Construct a 98% confidence interval about mu if the sample size, n, is 17. (b) Construct a 98% confidence interval about mu if the sample size, n, is 28. (c) Construct a 99% confidence interval about mu if the sample size, n, is 17. (d) Could we have computed the confidence intervals in parts (a)-(c) if the population had not been normally distributed?
sample mean = 110
standard deviation = 10
a) n = 17 df = 16
98% confidence interval t = 2.584
standard error = = = 2.425
= 110 2.584(2.425)
= 110 + 6.266 = 110-6.266
upper bound = 116.266 lower nound = 103.734
b)
sample size n= 28
df = 28-1 =27
98% confidence interval t(alpha/2) = 2.584
standard error = = 10/sqrt(28) = 1.889
= 110 (1.889)(2.584)
= 110+4.881 = 110-4 .881
upper limit = 114.881 lower limit = 105.119
c)
99% confidence interval
n =17 df = 16
t(alpha/2) = 2.921
standard error = = = 2.425
= 110 2.921*2.425
= 110+7.083 = 110-7.083
upper limit = 117.083 lower limit = 102.917
d)
NO, if the population had not been normally distributed we could not compute the confidence interval