EoghanONeill

An alternative is to permute the dependent variable a number of times to obtain a null distribution for the importance measure, and then obtain a p-value. This approach is used...

I include below some code for a simulation study for variable importance tests based on permutation of the dependent variable. This code takes several hours to run. Perhaps the authors...

I think permuting treatment assignment is a good suggestion. It gives similar results to the simulations above. Also, the measure based on permutation of the dependent variable should be interpreted...

Also, the predicted value when it does not crash is ``-0.977252'', which is less than the sum of the minimum terminal node values obtained from each tree. Maybe this is...

Also the training data predictions obtained from ``$predict()`` are different to those obtained from ``getPredictionsForTree( )`` ``predict( )`` gives the same predictions as ``$train`` after I run the sampler. Therefore...

I think the tree terminal node values are not on the original scale, so it is necessary to transform back from the scale between -0.5 and 0.5 to the original...

I have received the same error message for the ``dbarts`` function. A different error occurs if the test and training data contain the same number of observations. The error message...

Thank you for testing the method for updating the splitting probability. I can confirm that when I test out the method with your simulated data one of the variables obtains...