A market researcher wants to evaluate car insurance savings at a competing company. Based on past studies he is assuming that the standard deviation of savings is $100. He wants to collect data such that he can get a margin of error of no more than $10 at a 95% confidence level. How large of a sample should he collect?
#we are given
sd<-100
#margin of error <= 10
#confinence interval is 95%
#caluculate significance level α that shows the probability of making the wrong decision
alpha <-1-0.95
alpha
## [1] 0.05
We are asked to find the minimum sample size that returns a margin of error of no more than $10 at a 95% confidence level.
A margin of error tells how many points (or percentage points) your results will differ from the true population mean.
In our case, a 95% confidence interval with a 10 points margin of error means that our statistic will be within 10 points of the true population mean 95% of the time.
Margin of error = z * SE
z * SE <= 10
z = 1.96
pop_mean<-0
se<-1
#bulding standard normal distribution curve for a population
visualize.norm(stat=c(-1.96,1.96),mu=pop_mean,sd=se,section="bounded")
Z<-qnorm(alpha/2, mean=0, sd=sd,lower.tail=F)/100
Z
## [1] 1.959964
1.96 * SE <= 10
SE = SD/sqrt(n)
1.96 * SD/sqrt(n) <= 10
n <-(1.96*sd/10)^2
round(n,0)
## [1] 384
n <-(Z*sd/10)^2
round(n,0)
## [1] 384
In order to receive a margin of error of no more than $10 at a 95% confidence level the minimum sample size is 384 (equal or greater than 384)