Hi
On Thu, 1 Apr 1999, Dennis Goff wrote:
> Stuart McKelvie asks:
> Also: Should we have another name for the "independent" variable
> when
> it is not truly experimentally manipulated? And should we have
> another name for the "dependent" variable in this situation?
> We have wrestled with this problem within our department. Some of us prefer
> to call these variables "independent" because of their place in statistical
> analyses. That certainly makes things easier for our students, but I argue
> that the label "independent" should be reserved for those variables that the
> experimenter manipulates. We have generally agreed to call these variables
> "non-manipulated independent variables." In truth that is not entirely
> satisfactory to me. I would prefer to call them something like "organismic"
> (watch your spelling here) or "subject" variables. My preference for this
> label relates to another post I saw this morning (I can't remember who wrote
> it). Variables like age and gender are stand in variables and reflect the
> effects of a number of other things like experience, genes and their
> combinations. IMHO the latter label makes this point more clearly.
> The question about a new name for the dependent variable in this situation
> is one that I have not thought about. I am interested in reading others'
> thoughts about that idea.
My preference in these situations is to use the more neutral
terminology of correlation and regression. That is, call the
classes predictor and criterion variables, reserving independent
and dependent for predictor variables that are experimentally
manipulated and dependent for criterion variables in experimental
studies.
Best wishes
Jim
============================================================================
James M. Clark (204) 786-9313
Department of Psychology (204) 774-4134 Fax
University of Winnipeg 4L02A
Winnipeg, Manitoba R3B 2E9 [EMAIL PROTECTED]
CANADA http://www.uwinnipeg.ca/~clark
============================================================================
