It would be extremly useful to allow interaction with the tree in all "tree type" algorithms. E.g. identify competitive splits, define a user splits

Hello, it would be interesting if you add normality test and homogeneous test before ANOVA test. In this case, XLSTAT could say "You can use ANOVA because your data respect hypothesis of ANOVA" or "Your data are not adapted for ANOVA test, do you ...

It would be great to be able to generate Markovian chain process in DoE menu of Conjoint Analysis

Robust PCA is as the name implies a more robust version of PCA. Extremely useful for large but sparse datasets (many biological areas e.g. ecology, metabolomics, transcriptomics; and computer science e.g. visual recognition).Provides a PCA which i...

为什么它有用，谁会从中受益，它应该如何工作？

You should adapt your simulator to include the zero/none option. Without it one cannot study market expansion and primary vs. secondary demand. It’s easy to do since you already have the zero option. For example, with the logit (beta=1) rule all o...

In control charts, it could be very informative to have a confidence interval to the number of Parts Per Million lying outside the tolerance boundaries.

The sensory scientist

Sometimes I have large data sheets with a lot of cells that contain missing values. Especially when the cells content comes from an array formula there is no feasible way to manipulate the cells by search and replace. I'd like to suggest that the...