Ganzfeld Experiments

[fls]

That seems to contradict the batting average example you pointed me toward. As the Wikipedia article notes, a batting average for a small number of at-bats can be highly misleading, but is highly meaningful over several thousand at bats. Similarly, it seems to me, the results of a single Ganzfeld experiment with a small number of trials can be highly misleading, but, when grouped with a number of similar experiments, the results can be highly meaningful. One of the experiments analyzed by Milton and Wiseman had four trials with two hits -- what possible conclusion can be drawn from that one experiment, if it is not grouped with other experiments?

But you did notice how it could lead to a reversal of what conclusion would be drawn, right?

That's the point of grouping them together, but you need to choose a way that doesn't introduce a bias of its own. If the conclusion drawn from treating them all as one study is the opposite of that drawn from treating them as separate studies, all you've done is substitute the effect with a bias. And we are more interested in the effect than we are in the bias.

What do you believe is the bet way to combine the 30 studies analyzed by M&W, and what overall probability would that produce?

If it were me, I'd go with one of methods I'm familiar with. But if I'm trying to persuade a particular audience, I guess I'd pick something they were familiar with (if it was all six-of-one and half-a-dozen-of-another).

I haven't done an analysis of M&W stuff, but I probably should. It wouldn't be that much work to input for something like this. I'm behind on some other stuff already, though (like trying to figure out the Stouffer z under these circumstances ).

Linda