In the Logistic platform, the logistic probability plot illustrates the model fit. The vertical axis on the right side of the plot is partitioned proportional to the count of observations for each level of the Y variable. There is a curve in the plot for all but one of the levels of the Y variable. The curve is the predicted cumulative probability up to and including the corresponding level of the Y variable. The vertical axis on the left side of the plot is on a probability scale. The predicted probability for a specific level is measured as the vertical distances between the curve for that level and the curve below the level.
The points in the logistic plot represent the observations from the data table. The horizontal position of each point is determined by the value of the continuous X variable for that point. The vertical position of each point is determined by the value of the categorical Y variable for that point. Each point falls at a random vertical position between the curve for its level and the next lower curve. This vertical jittering of the points makes it easier to see where the points are most dense, but the vertical position does not directly correspond to the values on the vertical axis. Because a fixed random seed is used, the vertical positions do not differ across multiple fits of the same model.