Statistical Computing 2

This set of portfolios contains the notes that were submitted for the second statistical computing module in the COMPASS CDT.

To view these portfolios, please see the menu bar on the left. You may have to scroll down.

In general, these notes form more advanced statistical computation methodologies, using a lower level language than R: C++. C++ is beneficial for its speed advantages over interpreted languages such as R or Python. This makes it a good candidate for computationally intensive methods such as Bayesian MCMC sampling, or when working with big data.

Most of my statistical work has been using R, so this module was a good opportunity for me to learn C++, and develop my Python skills. In general, I still prefer R to Python for basic data analysis for its simplicity, but there are a lot of cases (such as neural networks in TensorFlow) where Python is superior. It is important to be able to know both.