AP Statistics Confidence Intervals for Means and Proportions

2000 children were surveyed and the report that followed said, "With 98% confidence, between 20% and 50% of all parents make their children eat breakfast." What does 98% confidence mean in this situation?

• We can be 98% confident that the method used to get the intervals always gives the correct answer

• 98% of all parents will make their kids eat breakfast

• When used repeatedly, the method used to find the interval produces intervals which include the true proportion about 98% of the time

• The kids were 98% confident that they ate breakfast that day.

Mrs. Soto polled 1000 adults and estimated with 90% confidence that the proportion of adults who have dessert after dinner is .75. Ms. Libner thinks that 90% confidence isn't enough and wants to do a 95% confidence. How would a margin of error for 95% compare with a ME for 90% if the same sample size was used?

• It would be smaller because a higher confidence means a smaller MOE

• It would be larger because a higher confidence means a larger MOE

• It would be the same because the sample size is the same

• Won't be able to tell without knowing the true parameter

The heights of 5-year old boys are approximately normal. The mean height of a random sample of 37 5-year old boys is found to be 30 inches with a standard deviation of 3 inches. What is the standard error of x̄?

• .493

• 1.32

• 5.77

• 1.96

A survey of a random sample of 2500 adults who have a credit card found that 570 had a balance of $1000 or more on their credit card.

What would NOT be a condition we need to verify before constructing the interval?

• np̂ ≥ 10 and n(1-p̂) ≥ 10

• n ≥ 30

• 10% condition

• random sample

A survey of a random sample of 2500 adults who have a credit card found that 570 had a balance of $1000 or more on their credit card.

What symbol would you use to describe the parameter?

• μ

• p

• p̂

• x̄

Scores on the mathematics part of the SAT exam in a recent year were roughly Normal with mean 515 and standard deviation 114. You choose an SRS of 100 students and average their SAT Math scores. Suppose that you do this many, many times. Which of the following are the mean and standard deviation of the sampling distribution of x̄ ?

• Mean = 515; SD = 114

• Mean = 515; SD = 114/√100

• Mean = 515/100; SD = 114/√100

• Mean = 515/100; SD = 114/100

• Mean = 515/100; SD = 114/√100

A newborn baby has extremely low birth weight (ELBW) if it weighs less than 1000 grams. A study of the health of such children in later years examined a random sample of 219 children. Their mean weight at birth was x̄ = 810 grams. This sample mean is an unbiased estimator of the mean weight in the population of all ELBW babies, which means that

• In all possible samples of size 219 from the population, the mean of the values of will equal 810.

• In all possible samples of size 219 from this population, the mean of the values of will equal μ

• As we take larger and larger samples from this population, x̄ will get closer and closer to μ .

• In all possible samples of size 219 from the population, the values of will have a distribution that is close to Normal.

• The person measuring the children’s weights does so without any error.

Why is it important to check the 10% condition before calculating probabilities involving x̄?

• To reduce the variability of the sampling distribution of x̄

• To ensure that the distribution of x̄ is approximately Normal

• To ensure that we can generalize the results to a larger population

• To ensure that x̄ will be an unbiased estimator of μ.

• To ensure that the observations in the sample are close to independent.

One reason for using a t distribution instead of the standard Normal curve to find critical values when calculating a level C confidence interval for a population mean is that

• z can be used only for large samples

• z requires that you know the population standard deviation

• z requires that you can regard your data as an SRS from the population

• z requires that the sample size is at most 10% of the population size

• a z critical value will lead to a wider interval than a t critical value

Which of the following would not decrease the width of a confidence interval?

I. Increasing the sample size

II. Decreasing the degrees of freedom

III. Decreasing the confidence level

• I only

• II only

• III only

• I and II only

• II and III only