Data modelling for analytics

Decision analytics methods have been very useful for strategic business planning in recent years. Analytics culture is an indicator of future strategic success. Data modelling plays an active role in building a data-driven culture. A seamless and consistent data model requires standard, compatibility and predictability across systems. A roadmap by assessing challenges and matching them with relevant data and resources leads to new opportunities to prioritize on.

Identifying relationships between entities of a dataset

The relationships between various entities of a dataset are similar to the relationships between objects in the real world. A dataset structured for one model is difficult to integrate with a dataset structured for another model. A thorough understanding of the attributes and entities of the data and their relationships helps to organize it to achieve the goals. A properly conceptualized data model enlightens the semantics of the subject area. Furthermore, a properly conceptualized data model helps to run various analysis such as regression with minimal redundancy.

How to interpret results from the correlation test?

Correlation is a statistical measure that helps in determining the extent of the relationship between... More

Customer database formation to build customer relations

A customer database, for small businesses often start out as a small excel worksheet whereas... More

Performing Canonical Correlation Analysis (CCA)

Until recently, Karl Pearson Correlation analysis was one of the most popular methods to measure... More

Exploratory model analytics

It is apparent that there is a strong realisation from the decision-makers on the appropriate handling of uncertainty. A model-based decision support system uses computational experiments to analyze complex and uncertain challenges. With exploratory modelling, multiple hypotheses can be tested by the means of computational experiments. The exploratory model analysis is one of the promising methods that support extensive analyses at relatively low costs. Based on the recommendations from the exploratory model analysis the decision-makers can make informed decisions.

Work sequence
  1. Conceptualize the problem.
  2. Explore uncertainties relevant for analysis.
  3. Develop a computational model.
  4. Perform computational experiments.
  5. Specify a criterion for selection.
  6. Visualize the outcomes of computational experiments.
  7. Make recommendations.
How to interpret the results of the linear regression test in SPSS?

The test found the presence of correlation, with most significant independent variables being education and... More

Performing pooled panel data regression in STATA

The underlying assumption in pooled regression is that space and time dimensions do not create... More

How to perform Panel data regression for random effect model in STATA?

The previous article (Pooled panel data regression in STATA) showed how to conduct pooled regression... More