The average posterior probabilities in the "prediction period" are outputted as final predictions, and predictions of this method is denoted as "IMRF2".
Even though the approach by Nam [77] is applied directly to the application of software module defect prediction, this method can be used for other applications.
The composition predictions using this method is compared with partial least square (PLS) and regression analysis (RA) methods to show its superiority over these other conventional methods.
We show that the theoretical predictions of this method are generally consistent with empirical expressions (from field data) and also laboratory rock experimental data.
However, the comparison is based on the MSN applied with k = 5, which produced the most accurate predictions with this method.
When making future predictions using this method, estimates varied depending on which approximation with which they were calculated.
Later, we confirmed the predictions of this method by our independent experiments in vitro under both equilibrium [ 79] and nonequilibrium [ 80] conditions of the electrophoretic mobility shift assay (EMSA).
The prediction by this method presents the representative retardation behavior and agrees with the experimental data.
The accuracy of crack depth prediction using this method has been verified by fractography of fatigue cracked rods.
Sometimes, exclusively data-driven models are also used in VLE prediction although this method too possesses drawbacks such as a trial and error approach in specifying the data-fitting function.
