Positive likelihood ratio

Method

Pooled positive likelihood ratio of an index test against a reference standard — sensitivity divided by one minus specificity — estimated in a bivariate or hierarchical random-effects model. Index test, reference standard, and decision threshold recorded on the edge.

The method is part of the endpoint identity. Studies measuring the same quantity by a different method are held as separate endpoints.

Notes

SIGN INVERSION against the negative likelihood ratio, which is computed from the same 2x2 table and reported in the same sentence of the same abstract. This one improves by RISING away from 1 (values above 10 rule a diagnosis in); the negative ratio improves by FALLING toward 0. Mapping one onto the other reverses the finding exactly. Also distinct from the diagnostic odds ratio, which is the quotient of the two and collapses rule-in and rule-out performance into a single number that cannot be separated again, and from pooled sensitivity, which is only one of this ratio's two inputs.