In this video, I'll provide the simplest and the most effective ways to explore data in R, which will significantly speed up your work. Moreover, we'll go one step beyond EDA by starting to test our hypotheses with simple statistical tests... that's what I call "deep" here.
If you only want the code (or want to support me), consider join the channel (join button below any of the videos), because I provide the code upon members requests.
You of coarse don't need to see the whole thing:
Timetable:
00:50 - automated reports as a separate video ( • Automated Exploratory Data Analysis (... )
02:44 - exploring categorical variables
05:00 - descriptive statistics with some basic tests, like Fishers and Chi-Square, Mann-Whitney and Kruskal-Wallis tests
09:15 - explore distribution with skewness and kurtosis tests
13:03 - explore normality with Quantile-Quantile plots and Shapiro-Wilk normality test
17:20 - compare groups with box-plots and non-parametric tests, like Mann-Whitney and Kruskal-Wallis
19:12 - explore and visualize correlations and get correlation coefficients, confidence intervals and p-values
24:03 - explore linearity of data with non-linear models and ggplot2 package
24:30 - explore and impute NAs as a separate video ( • R demo | How to impute missing values... ) and outliers (part of this video)
Here is the code and article about or instead of this video: https://yuzar-blog.netlify.app/posts/...
By the way, one of the songs playing in the background is called ”Hypothesis” by the artist Vincent Rubinetti 😉
Music by Vincent Rubinetti
Download the music on Bandcamp:
https://vincerubinetti.bandcamp.com/a...
Stream the music on Spotify:
https://open.spotify.com/album/1dVyjw...
Enjoy! 🥳
Watch video DEEP Exploratory Data Analysis (EDA) | explore your data and start to test hypotheses online without registration, duration hours minute second in high quality. This video was added by user yuzaR Data Science 20 April 2021, don't forget to share it with your friends and acquaintances, it has been viewed on our site 14,127 once and liked it 592 people.