Hi I've never understood the methods first rationale, and argued strongly about 20 years ago for stats first, which we have had since. My reasoning:
1. difficult to teach some methods concepts without stats (e.g., reliability), and it helps for others (e.g., computing Ms for two randomly divided samples to show that, on average, equality results from random assignment; smaller error term for within-s than between-s comparisons, ...) 2. having stats allows one to reinforce it during methods; analyzing results of some demo for randomization or counterbalancing; computing Ms, SDs, and split half rs for measurement; ... Given methods first, seems to me that one must end up teaching stats or else not do a very deep intro to concepts. Take care Jim James M. Clark Professor of Psychology 204-786-9757 204-774-4134 Fax j.cl...@uwinnipeg.ca >>> Michael Smith <tipsl...@gmail.com> 14-Apr-10 1:18:28 PM >>> Thank you for all of the advice :-) Hmmmm..... Well it would be a separate methods course and a separate stats course with a 1 hour lab component. The students would be majors but this would be a first stats and first methods course (and I suppose maybe their only one for undergrad) Methods would come first (if y'all thinks that makes a difference about how to teach it). I've never heard of the Cozby text. Which text is it? --Mike --- You are currently subscribed to tips as: j.cl...@uwinnipeg.ca. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13251.645f86b5cec4da0a56ffea7a891720c9&n=T&l=tips&o=1951 or send a blank email to leave-1951-13251.645f86b5cec4da0a56ffea7a89172...@fsulist.frostburg.edu --- You are currently subscribed to tips as: arch...@jab.org. To unsubscribe click here: http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=1954 or send a blank email to leave-1954-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu
