Causal Relationships

Causal Relationships - Causal Relationships If we wish to...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Causal Relationships If we wish to conclude that X causes Y, 3 conditions must be met 1. There must be an association between X and Y. Sometimes people will say that X and Y must be “correlated,” but I actually prefer the term association in this context. For the person on the street, association and correlation are probably synonyms. For the statistician, however, “correlation” refers to a specific set of techniques used to measure associations between two or more variables. So, I prefer the more general (and broad) term association. 2. X must occur before Y. This is typically referred to as the time-order, or temporal ordering, condition. This is a logical condition of cause, of course, but it one that is easily missed. If there is a negative association/correlation between smoking marijuana (X) and grades (Y), is it X causing Y, or Y causing X? 3. The relationship between X and Y cannot be spurious… or accidental. Often it is a third variable that essentially causes the association between X and Y. Rape rates and ice cream sales are associated only because a third variable (temperature) is associated with both. 2 Research Designs: One very good at establishing causal relationships, one not so good. It is, no doubt, an oversimplification to suggest that there are only two research designs. There are many many research designs. But, for the purposes of this discussion, I think it is reasonable to suggest that there are two; experimental designs and non-experimental designs (also sometimes called association/correlational designs). Experimental Designs – The Mercedes of research. This is the only way to go if you can pull it off (but often you can’t). With experimental designs you essentially satisfy conditions #2 and #3 above. You have an experiment if
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 3

Causal Relationships - Causal Relationships If we wish to...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online