Modelling and Predictions are bread and butter of many Statistical applications. Due to the evolution of Big data, the statistical applications have emerged bigger and bigger and have achieved a remarkable milestone in every single field. Several researcher and scientists have mentioned the importance of modelling and predictions. They have become part of every field and exhaustively utilized in most of the applications. The remarkable idea of applying these modelling by the researchers and academicians are primarily for budgeting, forecasting in several fields like finance, economics, healthcare, business and industries.
Even though it might sound weird, it needs to be understood that we need to have prior knowledge about modelling or predicting for any field or using any particular datasets. That is, the analyst should have some knowledge about the application. For example, when we wish to proceed with budgeting for the next fiscal year of a Healthcare Business Processing Outsourcing (BPO), we need some prerequisite knowledge about healthcare sector or about BPO.
Many readers would have an impression right now I am speaking about Bayesian and proceed further with an Bayesian data analysis. Indeed, it is not wrong to work over Bayesian perspective, but at this point in time, I am not moving towards Bayesian. In this context, prior knowledge means the opinion of the expert or concerned person in that particular field who would serve as a support to achieve proper and appropriate modelling. The interpretations require extra efforts with the help of expert opinions which would lead to a successful model. This visual depiction will clearly describe them with simplicity and it does not require any source of explanations. The below depiction will help us in building model which might be helpful for practitioners.
Comments
Post a Comment