Correlation does not imply causation because a correlation between two
variables may be caused by some third variable that the researcher ca
n sometimes be controlled, even when the variables are not measured, a
nd even when they are unknown. The article will discuss linear structu
ral relations (LISREL), Two Stage Least Squares (TSLS), and path analy
sis as statistical procedures that sometimes permit causal inferences
from correlational findings.