We generally do not know the number of classes in advance. Thus, we need to test for goodness of fit or we may just be looking at statistical noise. Please consider adding the cophenetic correlation coefficient (Sokal and Rohlf, 1962 or Farris) or...

For nonlinear regressions add Akaike Information Criteria for finite samples goodness of fit

This is an important and useful tool in testing the significance of multivariate statistics...it is used in environmental community analysis...e.g. comparing the abundance of species composition in two different localities. It is frequently used ...

Currently, XLSTAT DoE for Conjoint, CBC & Maxdiff generates the same questionaire to all respondents. It would be great to be able to generate different question sets to give to different respondent groups.

Principal Component Analysis (PCA): an option that allows displaying variable tags parallel to vectors in the correlation circle could help improve visibility in some cases. Example: http://i.stack.imgur.com/PDYH3.png

It would be great if XLSTAT allows taking into account prohibited pairs in CBC designs.

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 ...

Cronbach's Alpha is alread available in XLSTAT's Factor Analysis options. Would be awesome if it could be accessible as an independent feature, along with other reliability indices, such as Guttman's lambda

The XLSTAT non parametric tests list is quite complete. One essential feature is missing, though: the Wilcoxon one-sample test to compare the location of a sample to a hypothesized value.