data-science-education

I was pleased finally to see a new R introduction especially directed at social scientists. The book title “Introduction to R for Social Scientists: A Tidy Programming Approach” (abbreviated I2RSS) was promising for me for two reasons. Read the full book review.

In this post, I summarize my learning problems to advance from an intermediate R level. I suggest finding projects you are interested in and inspecting their codebase at GitHub. In a certain sense, you could use the skills of those experienced persons who guide the project/repository for mentoring your own learning advancement via GitHub. Maybe there is even a possibility of getting involved in the project and learning from relevant real-world challenges. — My example is with R and GitHub, but the learning strategy I recommend here should be usable for other programming languages and other collaborative version control systems.

Beginning in December 2016, I initiated a new personal enterprise: Learning the statistical programming language R to acquire competencies of a data scientist. The post reports on my experience with a shortcoming on a coursera course and argues that even advanced MOOCs are often not designed to meet the particular requirements of self-determined learners. With the example of learning all the different ways to get data into the R environment, I show that designing different learning paths for different learner needs could be a solution.