When dealing with the statistical analysis we usually want to have normally distributed data. It is due to the fact that the vast majority of statistical tests are interpretable only when we use them on normally distributed data points.

However, if our data is non-normal, we may want to investigate the cause and perform relevant transformations to obtain a roughly normal distribution. One of the most popular methodology to achieve that is the Box-Cox transformation.

Transforming the data means performing the same data operation on each part of the dataset. …

The world is not linear. It is a simple statement that everybody is aware of. However, it entails meaningful consequences to our modeling approaches. The vast majority of models used in academia and industry are linear models.

The assumption of the linearity of phenomena under consideration is highly arbitrary. It is usually necessary for research that encompasses a small number of observations because it facilitates parameter estimations. When we have a larger sample of observations, we may consider non-linear dependencies between dependent and independent variables. To afford this, we may want to estimate a non-linear model. These kinds of models…

**TOPSIS**, known as **T**echnique for **O**rder of **P**reference by **S**imilarity to **I**deal **S**olution, is a multi-criteria decision analysis method. It compares a set of alternatives based on a pre-specified criterion. The method is used in the business across various industries, every time we need to make an analytical decision based on collected data.

Let’s imagine the situation when we want to compare several companies and find out which one has the strongest financials. These companies are our alternatives set. To combine them together and decide which one is the strongest, we need to employ some reliable metrics. In such a…

Quantitative Analyst hunting for alpha. Passionate about market research, automatization, and non-obvious solutions utilizing alternative data.