Statistics

Naive Bayes

Support Vector Machine.

Here you will learn approaches to split your data into subsets - train and test for your modeling.

Examples of Neural Network classification using Neuralnet R package.

Unsupervised method for dimentionality reduction - Uniform Manifold Approximation and Projection (UMAP).

Here you can find how to work with hierarchical cluster analysis, how choose number of cluseter and how to choose the best model.

Logistic regression

Hypothesis testing.

Model evaluation metrics.

Here, we will consider a simple example of Markov process with implementation in R. The following example is taken from Bodo Winter website. A Markov process is characterized by (1) a finite set of states and (2) fixed transition probabilities between the states. Let’s consider an example. Assume you have a classroom, with students who could be either in the state alert or in the state bored. And then, at any given time point, there’s a certain probability of an alert student becoming bored (say 0.