Prediction of x values from given y values. For more information, see Inverse Prediction.
Is useful only if you have several points for each x-value. In these cases, you get reasonable estimates of the rate at each value, and compare this rate with the fitted logistic curve. To prevent too many degenerate points, usually at zero or one, JMP only shows the rate value if there are at least three points at the x-value.
Produces a lift curve for the model. A lift curve shows the same information as a ROC curve, but in a way to dramatize the richness of the ordering at the beginning. The Y-axis shows the ratio of how rich that portion of the population is in the chosen response level compared to the rate of that response level as a whole. See the Fitting Linear Models book for details about lift curves.
Suppose you have an x value that is a diagnostic measurement and you want to determine a threshold value of x that indicates the following:
A condition exists if the x value is greater than the threshold.
A condition does not exist if the x value is less than the threshold.
For example, you could measure a blood component level as a diagnostic test to predict a type of cancer. Now consider the diagnostic test as you vary the threshold and, thus, cause more or fewer false positives and false negatives. You then plot those rates. The ideal is to have a very narrow range of x criterion values that best divides true negatives and true positives. The Receiver Operating Characteristic (ROC) curve shows how rapidly this transition happens, with the goal being to have diagnostics that maximize the area under the curve.
Sensitivity, the probability that a given x value (a test or measure) correctly predicts an existing condition. For a given x, the probability of incorrectly predicting the existence of a condition is 1 – sensitivity.
Specificity, the probability that a test correctly predicts that a condition does not exist.
A ROC curve is a plot of sensitivity by (1 – specificity) for each value of x. The area under the ROC curve is a common index used to summarize the information contained in the curve.
Related Information 
The Save Probability Formula option creates new data table columns. These data table columns save the following:
Inverse prediction is the opposite of prediction. It is the prediction of x values from given y values. But in logistic regression, instead of a y value, you have the probability attributed to one of the Y levels. This feature only works when there are two response categories (a binary response).
The Fit Model platform also has an option that gives an inverse prediction with confidence limits. The Fitting Linear Models book gives more information about inverse prediction.
Related Information