477 / 762
Chapter 11: Confidence Intervals – Large Samples
477
Note:
We
do not
say that the probability is 0.95 that the population
proportion of people who, when they purchase a new vehicle and who do not
consult a consumer ratings publication such as Consumer Reports, is between
0.6792 and 0.8008. Once the sample is obtained and the confidence interval
is constructed, the population proportion of people who when they purchase a
new vehicle and do not consult a consumer ratings publication such as
Consumer Reports, will be in the interval or it will not be in the interval.
Note:
The repeated sampling interpretation of a confidence interval can be
applied to any confidence interval for any population parameter.
Sample Size Needed to Estimate a Population Proportion
Sample size determination is closely related to estimation. You may need to
know how large a sample is necessary in order to make an accurate estimate
for a population parameter. Here we will concentrate on the population
proportion
. The answer depends on:
The margin of error
The point estimate for the population proportion
The degree of confidence
For example, you may need to know how far away from the population
proportion you would like the estimate to be, and how confident you are of
this. Since,