0
$\begingroup$

I have a question about something that is asked. I've read to make a table of this by using a very large number (like 100.000), but I actually don't know where to start.

Suppose that there was a cancer diagnostic test that was 95% accurate both on those that do and those that do not have the disease. If 0.4% of the population has cancer, compute the probability that a tested person has cancer, given that his or her test result indicates so

Can someone please give me some directions? I want to understand what they mean...

What I had was that 400 people have a disease, given the fact that a test would be 100% accurate. Because it is 95%, I have "people with a disease" is 280... I mean, am I going the right direction with this?

If someone can show me how to calculate and put it in a table, I would be grateful.

$\endgroup$
3
$\begingroup$

The epidemiology says, 0.4% have cancer, that is in a table:

                test says
              yes       no      sum
true    yes                       0.4 %
cancer  no                       99.6 %

        sum                      100 %

The test is right in 0.95 of the cases and wrong in 0.05, thus

                      test says
                  yes          no         sum
cancer  yes     .95*.4%      0.05*0.4%    0.4 %
        no      0.05*99.6%   .95*99.6%   99.6 %

        sum                               100 %

This is enough to answer the question, but you will probably need to fill the rest of the table for the questions still to come.

$\endgroup$
  • $\begingroup$ Thanks! I'd preferred doing it with absolute values instead of percentages, but thanks. I'll sort it out. $\endgroup$ – Siyah Nov 21 '16 at 15:28
2
$\begingroup$

You shouuld also take into account the Bayes' Theorem to justify your answer.

https://betterexplained.com/articles/an-intuitive-and-short-explanation-of-bayes-theorem/

Try to understand it and consider the events:

A) Have the dissease

B) Have a positive diagnostic

to solve your problem.

$\endgroup$
  • $\begingroup$ +1 for bringing up Bayes even though the question asked for a table, going through it with a table and with Bayes theorem will help a lot in understanding. $\endgroup$ – Bernhard Nov 21 '16 at 15:18

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.