I have studied effect of two treatments on cells followed by combination of two treatments. It looks like a additive effect. However, I do not know about exact statistical test that can help me identify whether it is an additive or synergistic effect.
If the effect is additive, then when you do a regression you will get a significant coefficient for each treatment. If they are synergistic, then the interaction term will be significant.
In Stata
. regress outcome treatment1##treatment2
The main effects and the interaction term will be evaluated.
Mario's Stata command and mine are identical. The syntax A##B means main effects and interaction. It saves you writing out all the terms.
Hi
You should use factorial analysis as Mario said (Calculation of A, B and A*B).
An example from statistics applied to health science
If we were examining the effect of two variables, gender and premature birth, on health outcomes, we would describe any difference in health outcome scores between genders as a main effect. Similarly any difference in scores of full term/premature birth would be described as a main effect. The presence of an interaction effect implies that the effect of gender on health outcome varies as a function of premature birth status.
https://en.wikipedia.org/wiki/Interaction
Berenbaum's equation: CI=d1/D1+d2/D2...dn/D where CI=interaction index; d1,d2,'.dn=doses of the active compounds inside the mixture; D1,D2,'.Dn=doses of the active compounds that produces the same effect of the mixture. If CI = 1 there's no interaction, CI < 1 = sinergism, CI >1 = antagonism.
- Badges
- Science topic
- Similar topics
- Chemistry
- Pharmacology
- Pharmaceuticals
- Drugs