Find and interpret a 95% confidence interval for the difference in the proportion the lie detector says is lying between those lying and those telling the truth.

Refer to the data in Table C.5. These data, introduced in Exercise A.23 on page 147, involve participants who read either deceptive material or truthful material while hooked to a lie detector. The two way table indicates whether the participants were lying or telling the truth and also whether the lie detector indicated that they were lying or not.

Table C.5

Exercise A.23

Is lie detection software accurate? A recent study was conducted in order to test the accuracy of a commonly used method of lie detection. The researchers are specifically interested in how lie detectors perform when an individual is stressed. A sample of 48 participants were gathered and attached to the lie detection device. They were asked to read deceptive material out loud while receiving an electric shock (to add stress). The lie detector failed to report deception in 17 of the 48 participants.

Detector Detector Says Lying Says Not Total Person lying 31 27 17 48 Person not lying 21 48