This discussion on models has really helped me get my head around the nature and status of models quite a bit. Thanks. It’s all a learning curve, and as with all iterative processes, I’m sure we’ll all find ourselves revisiting and revising our positions numerous times over the years to come.
I found a little single-page opinion piece about models that sums up my current views. Yesterday, Dr. A. wasn’t 100% sure of the George Box reference (“All models are wrong, but some are useful” — apparently it’s on page 424), and when I looked it up, Bakker’s summary of the purpose of models popped up.
Here are a few choice quotations from Bakker (2013, all p. 313):
“Stating that all models are wrong because they don’t equal reality makes no sense. I do not even want my models to equal reality–I already have reality.”
And:
“Whether a model is good or bad is inherently linked to the purpose of the model.”
Sometimes I find myself involved in convoluted self-discussions. Bakker is a welcome kick up the proverbial.
The figures you provide for drop-outs is interesting. At this stage, I don’t have an opinion on the matter; I’m just collecting data. This information certainly helps swing my thinking in a different way from yesterday. Thanks.