>
>As for sample size, it really depends on whom you're talking to and what
>you're doing with the data. For instance a single case design only uses 1
>subject (typically) and a hell of a lot of observations. A factor analysis
>(Principle Axes, Alpha or Maximum Likelihood) most prefer having at least
>500 to 1000. Getting into causal modeling/structural analysis can require
>tens of thousands. It all depends.
>
>larry
Hmm this is all beyond the basic political stats class that I took over 5
years ago.
The reason I made the model was to support a theory I had. The numbers
suggests that I may have been wrong.
I wish I could get a normal distribution on the age though. That would
suggest that I have enough data where I can start to make broad claims!
[Todays Threads] [This Message] [Subscription] [Fast Unsubscribe] [User Settings]
