Unit 9 - Inference on Proportions

Question 1

What is a confidence interval?

Answer 1

A range of numbers that are used to estimate a parameter.

Question 2

A higher confidence level produces a _______ confidence interval.

Answer 2

Wider

Question 3

A lower confidence level produces a _________ confidence interval

Answer 3

Smaller (skinnier)

Question 4

Interpret this 95% confidence interval: (.40, .46)

Answer 4

We are 95% confident that the true proportion of _______ is between .40 and .46.

Question 5

Interpret the 95% confidence level of this interval: (.40,.46)

Answer 5

95% of the intervals we construct in this way will contain the true proportion of ______.

Question 6

What are the 4 steps when conducting an interval or a statistical test?

Answer 6

• Define Parameters (& name test)
• Conditions
• Calculations
• Conclusion

Question 7

How do you know when to reject the null hypothesis?

Answer 7

If the p-value is low, reject the Ho. (p-value is lower than alpha)

Question 8

What is alpha ?

Answer 8

The significance level AND the probability of a Type I error

Question 9

What is beta (ß)?

Answer 9

The probability of a Type II error

Question 10

What is a Type I error?

Answer 10

The null hypothesis is true, but we think it’s not.

Question 11

What is a Type II error?

Answer 11

The alternative hypothesis is true, but we think it’s not.

Question 12

What is power?

Answer 12

The probability of rejecting a false null hypothesis

Question 13

What are two ways to increase power?

Answer 13

1. Increase alpha
2. Increase sample size (n)

Question 14

If you want to decrease the size of your confidence interval, what are two methods?

Answer 14

1. Decrease confidence level
2. Increase sample size (n)

Question 15

What are the 3 conditions for a 1 proportion z interval or test?

Answer 15

1. We have a random sample
2. We assume the population > 10n
3. The sampling distribution is approx normal because np and nq >10

Question 16

What are the 3 conditions for a 2 proportion z interval or test?

Answer 16

1. We have 2 independent, random samples.
2. We assume the population > 10n₁ and 10n₂
3. The sampling distribution is approx. normal because n₁p₁, n₁q₁, n₂p₂, and n₂q₂ >10.

Question 17

What or who do we put on trial during a hypothesis test?

Answer 17

the population parameter

Question 18

What is the parameter for a 2 proportion z interval?

Answer 18

p1 - p2

Question 19

What is the parameter for a 1 proportion z test?

Answer 19

p

Question 20

Which is used for a 2 prop z interval?

Answer 20

The first one

Question 21

Which is used for a 2 prop z test?

Answer 21

The second one