smc213I googled the meaning of abnormal test results just to make sure.
A positive test is one in which the result of the test is abnormal; a negative test is one in which the test's result is normal. +2019-07-14T18:05:48Z
This guy on youtube does a killer job on explaining all these problems. Just does problem after problem on 2x2 tables and a few other topics. The link to part 1 is added, part two you can find on the side panel I'm sure.
amirmullick3Not sure what lfsuarez and seagull above mean. Here is my explanation.
Specificity = TN/(TN+FP). This test gave 20 false positives out of 100 people, and only 15 true negatives out of 50 men.
Specificity also equals 1-FPrate, and here the FP rate seems 20% so 100%-20%=80%.+32019-06-17T20:27:10Z
yb_26abnormal test result means pt has cancer =>
TP = 35, FN = 15 (50-35), FP=20, TN =80 (100-20) => specificity = TN/(TN+FP) = 80/100 = 0.8 (in % will be 80%)
true negatives are 80 out of 100, not 15 out of 50+22019-07-13T21:02:07Z
bulgaineIf you replace the values from the question in the table of page 257 of FA 2019, yb_26 explanation is correct. Abnormal test = patient has cancer = test +
Question says 35/50 men with prostate cancer (so all 50 have cancer) only 35 have abnormal test results, meaning that TP=35 (disease + test +) and FN= 15 (disease + test - because they do have cancer but the test was not abnormal for them ).
20/100 men without prostate cancer have abnormal test results meaning all 100 DONT have cancer but 20 show that they have cancer when its not true so FP=20 (disease - test +) and TN =80 (disease - test -)+2019-07-18T20:09:16Z