CALIBRATION AND VERIFICATION OF RISK ALGORITHMS USING LOGISTIC-REGRESSION

The use of logistic regression is proposed as a method of verifying an d calibrating disease risk algorithms. The logistic regression model c alculates the log of the odds of a binary outcome as a function of a l inear combination of predictors. The resulting model assumes a multipl icative (relative) relationship between the different risk factors. Co mputer programs for performing logistic regression produce both estima tes and standard errors, thus permitting the evaluation of the importa nce of different predictive variables. The use of receiver operating c haracteristic (ROC) curves is also proposed as a means of comparing di fferent algorithms. An example is presented using data on Sclerotinia stem rot in oil seed rape, caused by Sclerotinia sclerotiorum.