I want to share my knowledge and experience to others and promote open science. I had only minimal education on data science – before our bachelor program was reformed – so I had to learn all things on my own, and I just know how hard it is. I once sat in a lecture and tried to understand MCMCMC before I even heard of Bayesian statistics. Such gaps are everywhere, especially after I started my master program.
Research is more like a process of self-teaching. More and more online resources for data analysis techniques are available as complement of conventional literature, but I found some of them lack clear introduction, or even proper documentation. Trying to understand and utilize these information can be very frustrating. Using R as an example here, which language I now use in daily basis since three years, is widely used by biologist for data analysis. I started to notice the change in challenging I face when coding with R comparing to the time when I just started - now I am familiar with logics in common R operations and some frequently used packages, but when I try to implement some ideas that have never be done by many people - which means there’s no ready-to-use function or package - I need to implement some functionalities from the scratch and it can get frustrating very very quickly. Another challenging is facing error message coming out from a deeply nested function inside a complex package. Both cases require more understanding in R and its ecosystem and a lot of effort and time to try out - which can be avoided for people having the same problem once someone solved them.
Long story short, my goal here is to put my posts in a way so that the audience, at least those doing similar things, maybe also people in different disciplines with different background, can benefit from the code I cracked, that hopefully inspires for cracking more code and making more cool stuff alive.
