How are control groups used in causal impact analysis?
As mentioned before, the core of the algorithm is to build a Bayesian structural time series model based on multiple Control groups and construct a synthetic time series baseline after adjusting the size difference between the Control groups and the Test group. So what are Control group and Test group?
What’s the difference between causal impact and synthetic control?
The difference between Synthetic Control and Causal Impact is that Synthetic Control uses only pre-treatment variables for matching while Causal Impact uses the full pre and post-treatment time series of predictor variables for matching.
How does causalimpact work in a control market?
The CausalImpact package constructs a synthetic baseline for the post-intervention period based on a Bayesian structural time series model that incorporates multiple matching control markets as predictors, as well as other features of the time series. We can summarize this workflow as follows:
How to use causal impact algorithm in exploratory?
So, basically we can use the DTW algorithm to find the most similar Control groups to the Test group and pass them to Causal Impact algorithm as predictors, then let the algorithm do the magic! And that’s how we implemented the Causal Impact algorithm support in Exploratory.
How is causal impact measured in the real world?
But, it’s actually hard to measure such impact in the real world because there are many attributes that can influence the outcome (e.g. page views). This is called ‘noise’.
What is a control group in a medical trial?
The control group receives either no treatment, a standard treatment whose effect is already known, or a placebo (a fake treatment). The treatment is any independent variable manipulated by the experimenters, and its exact form depends on the type of research being performed. In a medical trial, it might be a new drug or therapy.