Marc:
The most recent issue of Perspectives on Psy Science from APS has a special section on the Bayesian approach to testing. (Is that the one to which you refer?)
I don't know Bayesian testing that well but here in my personal opinion. Part of the appeal of the Bayesian approach is based on arguments about the misuse of the Fisher approach. I don't find that to be a strong argument. Just because your neighbor smashed his thumb with a hammer doesn't mean that the hammer isn't a useful tool.
If your students are grad-school bound then they need experience with thinking about the merits and demerits of null-hypothesis testing. Not thinking about null-hypothesis testing will not improve critical thinking about this approach.
Here would be my approach, I would teach up through the basic ANOVA to make sure that students understand that way of thinking and calculating, then I would teach basic Bayesian thinking and claculating, *and* then I would confront them with research problems to compare and contrast the Fisher vs. Bayes approach.
Ken On 5/19/2011 7:35 PM, Marc Carter wrote:
Hi, all -- Next year I've planned on developing a stats/methods integrated text (I have some sabbatical time). More and more, though, lately I've been reading that "we're doing stats wrong" and need to start moving to Bayesian stats. I understand and appreciate the arguments. I think they're right. The recent Psych Science has a bevy of articles about it, exacerbated, I'm sure, by Bem's JPSP article. Our program is essentially a grad-school-prep program, and the text will be for these students: all grad-school-bound, and smart. But most are going into the helping, rather than research-side of psych. But they'll get PhDs. Can I get a show of hands to help me decide whether or not I should a) include only Bayesian hypothesis testing, 2) both trad and Bayesian hypoth tests, or iii) just the trad stuff. It's a year-long course with a lab (I get them 6 hours a week for a year), and right now they come out knowing things all the way through mixed-model factorial ANOVA. Should I back off the hard-core experimental design (ANOVA) and move toward this recent (sorta) issue about how we have been doing hypothesis tests? What thinkest thous? m
--------------------------------------------------------------- Kenneth M. Steele, Ph.D. [email protected] Professor Department of Psychology http://www.psych.appstate.edu Appalachian State University Boone, NC 28608 USA --------------------------------------------------------------- --- You are currently subscribed to tips as: [email protected]. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=10650 or send a blank email to leave-10650-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
