Here\'s a real life example of how public health researchers weighed the harm of
ID: 3317053 • Letter: H
Question
Here's a real life example of how public health researchers weighed the harm of making Type I errors vs. Type ll errors When doing a screening test for HIV, the test that is used has a higher rate of false positives (Type l error), but a very low rate of fals If someone tests positive on the screening test, they do a follow-up test with a test th Discussion Prompt: Why do you think public health researchers decided that a Type I error was preferable to a Type Ilerror when it ca at has a lower rate of false positives came to HIV test results? Do you agree with their decision?Explanation / Answer
Given for doing a screening test on HIV, the test which is used has a higher rate of false positives that is Type I error but a very low rate if false negatives that is Type II error. In hypothesis testing we have null hypothesis say H0 . Now the test result may come out as positive that is in favour H0 or negative that is H0 is false. So in case of Type I error we reject the null hypothesis when it is actually true. In case of Type II error we accept H0 when it is actually false. The false positive error is a result that indicates something is achieved when actually not. So in this case we wrongly assume a positive result. The false negative is a result that when something is actually achieved but we wrongly donot believe the true condition. So in case false negative result we wrongly assume the negative result. Here a screening test has been done to detect HIV. The positive result show that one has HIV and negative is that one does not have HIV. In the question the result of the test is positive. So here we want to minimize the the error of wrongly accepting the positive result that is false positive as we have the screening test which has higher rate of false positive. As there is higher probability of false positive result in the screening test so when we get a positive result we want to minimize the Type I error in the follow-up test. So here we want a test which has lower rate of false positive rather than lower rate of false negative. So Type I error is preferable to Type II error when it came to HIV test results.