A successful data science project involves asking good questions, finding data that allows answering them, and possessing the skills and tools for actually doing so. In addition, communicating all this to others requires documenting the process in a transparent fashion.
Abundant amounts of data can easily be found online, but they were often collected mechanically or on the basis of rather rudimentary questions
(e.g., How does some variable vary as a function of some other variable? How does it change over time?). To become interesting and useful, data must be analyzed with good questions in mind.
- See Appendix B (especially Section B.3.3) for a list of data sources.
It is impossible to provide shortcuts for asking and answering good questions. Essentially, asking and answering questions is what science is all about. So be curious, ambitious, and dare to find out what you or others want to know.
There really is no shortage of theoretical and empirical questions in science. Explicating and answering them is a task that can be strenuous or enjoyable, but always requires a sound combination of data, tools, and skills.
[60_dsproject.Rmd updated on 2020-10-30 16:01:17 by hn.]