firstname.lastname@example.org wrote: > Hi guys and gals, > > As a newbie on these groups please forgive my cross-posting on > sci.stat.edu - I'm not sure which is the more appropriate forum. I'm a > graduate student in psychology trying to make sense of some stats > theory regarding "true" independent variables (as opposed to > quasi-independent or any other sort). > > To my understanding so far (based on stats books and online resources), > a true independent variable is one where the experimenter must sample > (or select) from prespecified groups rather than manipulate (or > randomly assign) to groups. The usual example I've seen is the > variable sex (male, female). My question is this: do true independent > variables only refer to participant groups or can they also refer to > stimuli/materials groups? > > For example, my experiment has a variable called stimulus type where > the levels are real words (e.g. CAT, VAT) and non-words (e.g. GAT, > JAT). Is stimulus type NOT a true independent variable because the > experimenter (me!) can only sample stimuli from the pre-specified > groups of real words (a finite set of 3-letter words in English) and > non-words (the set of 3-letter strings that are not real words in > English)? Or does its status as a true independent variable depend on > whether I run the experiment as a within-participants design (where > each participant sees both types of stimuli) or a between participants > design (where I randomly assign participants to one stimulus type)? > > Any and all help would be much appreciated. This question has my psy > colleagues all scratching their heads and has caused more than one > argument. > > Elle. >
I think you are confusing two issues. Bill H addressed the issue you raise in your 2nd paragraph--i.e., fixed versus random factors. (For those reading in sci.stat.edu, Bill's post appeared in sci.stat.consult only.)
But in the 1st paragraph, you are talking about the distinction between variables that the researcher can actually manipulate (e.g., dose of drug given to each subject) and those that can only be observed and recorded (e.g., age, gender), and you got it backwards. Variables that can be manipulated by the researcher are true independent variables.
-- Bruce Weaver email@example.com www.angelfire.com/wv/bwhomedir