A METHOD TO QUANTIFY DEVIATIONS FROM ASSAY LINEARITY

We present a statistical method to quantify deviations from linearity for assays that veer from linear assay responses. Our procedure handle s the common case of unequally spaced analyte levels and nonconstant v ariance and provides a least-squares estimate with a confidence interv al for the amount of deviation from assay linearity at a specified ana lyte concentration. This estimate of assay bias due to nonlinearity go es beyond the NCCLS EP6 lack-of-fit test, which tests for only the pre sence of nonlinearity. Knowing that nonlinearity is present is insuffi cient; users need to know the magnitude of the bias caused by nonlinea rity. Our method can also be used with multifactor designs that estima te other systematic assay effects such as drift and carryover, thus ob viating the need for a separate protocol to assess linearity. The proc edure is carried out by adding extra columns to the design matrix corr esponding to the concentration level(s) of interest. The extra columns , which replace the quadratic column, are orthogonal to all other colu mns. We describe a general method of constructing the new columns, and illustrate the procedure with a manual ammonia assay example dataset from EP6.