https://github.com/petzi53/ldsr
Learning Data Science with R (ldsr)
https://github.com/petzi53/ldsr
data-science learning-by-doing notes personal-project r
Last synced: 9 months ago
JSON representation
Learning Data Science with R (ldsr)
- Host: GitHub
- URL: https://github.com/petzi53/ldsr
- Owner: petzi53
- Created: 2021-12-11T18:04:37.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2022-01-02T09:17:52.000Z (over 4 years ago)
- Last Synced: 2025-01-22T13:52:43.459Z (over 1 year ago)
- Topics: data-science, learning-by-doing, notes, personal-project, r
- Language: HTML
- Homepage:
- Size: 1.49 MB
- Stars: 0
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Learning Data Science with R (ldsr)
This bookdown project will function as my personal notebook for learning data science with R.
Judging my knowledge state personally, I believe I am currently (December 2021) on an intermediate level in R. This in-between status of my working knowledge (not a beginner and not an expert) is precisely the reason why I started this notebook. It is difficult to advance on this intermediate level as a self-determined learner.
Reading newly published books on data science is not as effective as I would wish. Much of the material I already know, so I have to look for the hidden gems of knowledge that are new for me. But more importantly, some of the books do not incorporate the modern trend I am interested in: Using the `tidyverse` and `tidymodels` approach for data wrangling, data analysis, and data modeling.
Furthermore is my statistical knowledge poor. The historical reason is my distrust of the NHST (Null Hypothesis Significance Test) at a time I didn't even know of this notion and other related issues like p-hacking. Therefore I am also interested to learn more about the differences between frequentist and Bayesian approaches.
Up to now, I have written personal notes and ran code examples by accompanying specific books. But in the last weeks, it turned out that this approach is not very practical. I am exposed to new material from many different sources (books, blogs, vignettes of packages, etc.), where I want to jot down my reflections and experiment with the code snippets. Therefore I thought that a general (meta) notebook would help me advance more effectively.