Causal Effect Analytics is a data analysis approach that uses causal designs to analyse causal relationships, perform experiments, impact evaluations and to support evidence-based decision-making. The used tools and techniques belong to statistical-methodological field of Causal Inference – one of the most complex, but also the most rewarding data analysis approaches.
The subtle differences can be revealed with data analysis approaches which use experimental frameworks to design studies and analyse data. Causal inference is based on the experimental framework, thus, the Causal Effect Analytics services enable you to squeeze-out of data the most valid and informative insights.
We use a holistic approach to Causal Inference, which means that we combine the knowledge of causal designs with the knowledge of the analysed subject matter theory. Because we understand the importance of high quality data, we spend a significant amount of time developing the most appropriate causal design before proceeding with analysis of data.
A high quality data is a result of a well designed study and a carefully developed causal design.The “garbage-in, garbage-out” problem is overcome with a well-thought design. To avoid all sorts of biases, particularly when using behavioural data, a great deal of discussion is spent on eliminating biases. The use of statistical thinking is critical for this process as also understanding of cognitive biases.
If the answer to at least one of the above questions is YES, Causal Effect Analytics will not only be of great help but the method of choice. Learn about the workflow of this service below.
We e-meet to discuss desired and possible data solutions by exploring available data sets.
We bring in the science of causal inference to prepare a strategy for study design and data selection.
We e-meet again to discuss a suitable data design and a choice of data analyses that can be implemented.
We assist your data analyses team with implementation of design and analysis, or we do it for you.
The number of e-meetings depends on data solutions we look at. The non-disclosure agreements are part of our culture.
P R I V A C Y F I R S T.
Working with us on your project enables your data team to learn about the methods and techniques that we use in Causal Effect Analytics. Your team learns about foundations to analyse causal relationships, perform experiments and impact evaluations. This service is designed to transfer the know-how of Causal Effect Analytics to our customers.
Interested in learning about Causal Effect Analytics tools and techniques?
The importance of analysing causal relationships was recognised by this year´s Nobel Prize in Economics, awarded to Guido Imbens and Joshua Angrist for their research in Causal inference.