Critical thinking and pandemics v: tests
The ideal physician test would always be accurate and never gives false results. The actual medical tests, for a variety of reasons, 100% accuracy and a good test are usually 90-99%. This means that the test is always wrong. So how do you rate the test results?
Intuitively, a person seemed to be the same as (or no) the accuracy of the test. For example, if the COVID-19 test has 90% accuracy, then if you test the negative, it seems that you do not have 90% covid option. Or, if you try a positive, you can think of 90% chance to COVID. Although this seems to us reasonable, it is not created from a common mistake about the correct and conditional probabilities. I will keep the minimum mathematics math, as Barbie said, it’s hard.
So let’s say I test Covid positive and 90% of the test is accurate. If I think there is 90% chance, I have Covid, I’m probably wrong and here’s why. The mistake failed the probability that is not distinguished from the probability given by the yk x provided by X. In the event, it is positive effect Covid and, of course, no influence. Therefore, 90% specific tests Covid does not mean that 90% of those who test positive (cause) will be COVID (Cause). It means that 90% of those who have COVID (Cause) will test the positive (effect). So if I’m Covid, there is 90% option that the test will detect. If you think about the wrong way to look positive, there was 90% chance I had a covid. So what if I test a positive test I have a real opportunity Covidio is 90% accurate? The answer is I don’t know. But I know how to sort the math.
To find out my chance to have Covid, I should also know the percentage of false positives that occur with the test and, very important, the rate of infection. The basic rate of infection is the frequency cause. Using my completed test and a number of numbers, here is how math would go.
Suppose that 90% accurate test has a 10% false positive rate and 1% of the question population is contaminated. 1,000 per person per population:
- 10 people will have Covid
- 9 people with Covid will be positive.
- 990 people don’t have Covid.
- People without Covidik will test positive.
While 108 will be positive tests, only 9 of them will be covid. So a person who tests positive has been 8%, not 90%. With these conditions and numbers formed, I have a Covid, 90% option I will try positive. But if I try a positive, there is 8% option Covid.
At this point it can be tempted to think that testing is useless, but it would be a mistake. Tests are useful to collect data about infection rates. It is a greater chance of testing in populations with higher population infections, but the function function is more than a test function. To illustrate this, let’s run an example with a change, because the infection rate increases by 10%. 1,000 per person per population:
- 100 people will have Covid
- 90 who will test the positive 90s.
- 900 people don’t have Covid.
- Covidik 90 will test positive.
180 tests will be positive and 50% of them will be Covid. So if I try a positive for Covid, 50% option is Covid. Again, according to the hypothesis, the accuracy of the test, has not changed. Therefore, groups that know that we know that there will be higher infection rates will have better statistical results, but many uses will be for more statistical analyzes. The NPR gave an excellent discussion to test antibodies against Covid and also included the calculator that Math will do for you.
In terms of putting your trust in a test, such as an antibody test, to know whether or not to be a covid, is to keep in mind the mathematics. Although it survives, even if it gives an immune, a positive test can say that the 8% option you had Covidium. Until we know the rate of an infection, we would guess in mathematics. A rational view of the pandemia can be strange: you should assume that you have Covid, as well as assuming that you do not have Covid. The same will be applied to the next pandemic.
