Why Doesn't Tetrad...? |
- Because those statistics can easily be obtained in Excel or Matlab
- Because this can be done in common commercial packages
- Same answer.
- These regression procedures could be valuable in estimating parameters in Bayes nets, but they require a sound search procedure for selecting interaction terms, and we haven't solved that yet.
- Probably it should. For many problems, however, the latent variable search procedure in Tetrad is preferable.
-Relevant statistics are available only for Normal, Multinomial and Conditional Gaussian distribution families; the last should be included.
- The models corresponding to a pattern could and perhaps should be provided, but their an infinite number of models consistent with a PAG, and your computer is finite.
- No consistent, computationally feasible, general algoirithms are known.
- No consistent search procedures are known.
- Bayes net search procedures can in principle be used for time series, but no practical, consistent, general search procedures are known. The search algorithms in Tetrad can be used to search for "simultaneous" causal relations after regression on lags.
- If the variables in one data set are a subset of those in the other data set, a common model can be sought with the present version of Tetrad. If the data sets have entirely distinct variable sets, no principled search procedure for a common model is possible. If the data sets contain some common and some distinct variables, a sometimes useful principled search is possible, but adequate algorithms have not yet been developed.