CAnoVa^© a Software for Causal Modeling

Abstract

The new impulse given in the last decade to the theory of individual and average causal effects is mostly due to the approach developed by Steyer and others and resulted in valuable theoretical results such as, for example, the link between unconfoundedness and causal unbiasedness. This approach has also allowed for the development of different practical procedures for both testing for confounding and for testing for (average) causal effects. The scope of this contribution is to present CAnoVa, a software for causal modeling that allows a straightforward use of these two methods. CAnoVa is fully compatible with SPSS and allows to test for confounding and for causal effects even in case of designs with multiple treatment variables and multiple confounders.