I think some people are forgetting that a government cannot give without also taking. There is no free lunch. A government that can give you everything you want is a government that can take from you everything you have.
Furthermore, some people are not being specific as to what metric by which they would judge any "stimulation", is it:
a) short-run real GDP
b) long-run real GDP
c) short-run real GDP per capita
d) long-run real GDP per capita
c) social welfare
All 5 have very specific and distinct meanings in economics, particularly the last, so I do not mean "social welfare" in the general sense of the word.
Furthermore to prove causation (say to prove event A causes event B) you have to look at the counter-factual i.e. what would have happened but for the event A.
Say you wanted to examine the effect of a drug on a patient. Simply showing that after taking the drug, the patient is in a better condition, doesn't prove it. What if the patient would have gotten better anyway? Who is to say that they would not have been in even better health had they not taken the drug? To get past this problem, drug trials typically have a "control group" who simply take a placebo (a sugar pill). Then the health of the control group is compared to that of the treatment group.
The argument that some people seem to be making is that if the "drug" (Rudd's stimulus package) is taken on today and you see an increase in GDP, then the spending package must have been good.