regression analysis suggestions?

[Jerry030]

Quote from jellob:

As MSJ indicated, your model is as good as the market allows. If your parameters work in one market but not another, your statistically meaningful result may not matter. I have recognized this fact, but still don't know how to take advantage of that. Maybe you can give me some ideas!

In contrast to the relatively simple regression approach you might want to consider using neural networks. It's a lot more work and a great deal more complexity both in development and execution but the results are better and more stable in different market conditions.

Psychology is an issue. Some people are uncomfortable using a black box approach. This is balanced against the ability of a NN to discover relationships and predictors that the human mind can't.