POPM 3240 Lecture Notes - Lecture 9: Multimodal Distribution, Type I And Type Ii Errors, Sensitivity And Specificity
Document Summary
Biomodally: unimodal curve a single peak, cutoff level must be set in order to distinguish normal and abnormal, in either unimodel or bimodel, it is easy to see the extremes and the normals. a (top-left), b (top-right), c (bottom-left), and d (bottom-right). This is also a type i error: if they tested + on gold standard but was - on the other test, they"re put into cell c and are deemed false negative. This c cell is also a type ii error: if participant tested - for both tests they are put into cell d and deemed a true negative, all participants must fall into one of these categories and all. Validity of screening tests: the validity of a test is defined as its ability to distinguish between who has a disease and who does not, we measure validity in two ways: test sensitivity and test specificity for short.