Statistics Know-how – Reaching the right conclusions from data

Whoever would like to reach specific conclusions from data would need methods of mathematical statistics.

• The descriptive or classical statistics (sums, units for central tendency and for the degree of randomness) are always at play when data is consolidated.
• The inferential statistics are required when decisions are to be made, as to what extent assertions from data samples can be generalised. Whether it is about the effectiveness of medication, the precision of medical measuring devices or the risk of credits – there is no way around the application of statistical models.
• Particular procedures of the model search – frequently known by the term Data Mining – search for structures and connections in the data to enable predictions. Examples are models that predict credit defaults, the purchasing behavior or the lapses of customers.
• Procedures of time series analysis forecast future values of a measurement series based on past values. This could for example be useful in the materials and storage planning. 

All our software engineers possess the necessary fundamental knowledge in mathematical statistics. Several employees (graduate of mathematics, graduate of business mathematics, graduate of computer science in medicine) are additionally particularly qualified and experienced in financial mathematics or medical statistics, so that we can always draw upon the required know-how.