[R-sig-eco] Teaching statistics to ecology undergraduates

[Graham Smith]

If, like me, you have a only a few hours (11 hours over 3 years in my 
case) to try and teach statistics to ecology undergraduates, how do you 
do it?

Any introductory statistics text seems to assume, more time and more 
mathematical ability than in practice is available.

Although, I emphasise graphical techniques and the use of confidence 
intervals, and how these might help understand the ecological process 
being looked at, I still spend a large chunk of precious time on 
hypothesis testing.

The more I have been thinking about this, and the more I search for a 
suitable text book, the more I realise how hopelessly confusing the 
average text book is, with t-tests, anova, manova, ancova, OLS 
regression, poission regression, logistic regression GLM etc. Yes I know 
that all of these may well not appear in the average introductory text.

I have reached the stage  where I am wondering whether I should just 
teach GLM. This would give the students a single flexible method capable 
of tackling a wide range of ecological problems. It would also,I think, 
provide a  better framework for approaching ecological questions than 
simple hypothesis testing.

I admit, that this email is really just me thinking out loud, but does 
anyone who teaches statistics to ecologists, or indeed anyone at all 
really, have any views about how best to spend my 11 hours (which I may 
be able to increase 13 hours).

I should point out that at the moment I also spend some of this time on 
good practice in data management, a bit on scientific method, and a bit 
on the importance of random sampling, but nothing really on experimental 
design.

Graham