#### Question 2706

As prevalence decreases, what happens to sensitivity?

#### Question 2707

As prevalence increases, what happens to specificity?

#### Question 2708

As prevalence decreases, what happens to specificity?

#### Question 2709

As prevalence increases, what happens to positive predictive value?

#### Question 2710

As prevalence decreases, what happens to positive predictive value?

#### Question 2711

As prevalence increases, what happens to negative predictive value?

#### Question 2712

As prevalence decreases, what happens to negative predictive value?

#### Question 2713

What feature of a specific test best accounts for its ability to “rule in” disease when the test result is positive?

#### Question 2714

What feature of a sensitive test best accounts for its ability to “rule out” disease when the test result is negative?

#### Question 2715

An ROC curve plots sensitivity versus 1-specificity. As sensitivity increases, what happens to specificity?

#### Question 2716

An ROC curve plots sensitivity versus 1-specificity. As specificity increases, what happens to sensitivity?

#### Question 2717

An ROC curve plots sensitivity versus 1-specificity. How could you rename the sensitivity axis?

#### Question 2718

An ROC curve plots sensitivity versus 1-specificity. How could you rename the 1-specificity axis?

#### Question 2719

Investigators plan a clinical trial to assess the ability of a new drug to lower blood pressure compared to an old drug. What is the null hypothesis?

#### Question 2720

A p-value is calculated assuming...

#### Question 2721

A p-value is the probability that the observed results...

#### Question 2722

A low p-value...

#### Question 2723

The lower the p-value...

#### Question 2724

A statistically significant result (p < 0.05) ...

#### Question 2725

A trial comparing a new antihypertensive drug to an old antihypertensive drug reports that the new drug results in 20 mmHg greater blood pressure reduction than the old drug. This result has a p-value of 0.02.

Assuming an absence of bias and that the null hypothesis is true, what is the best interpretation of this result?