Descriptive statistics - Lecture 4 - Data analysis using R

An example of a data API for Social Sciences. Lecture 4 contains the Answers (L3) and goes into Descriptive Statistics and how you can compute them with R. What are central tendencies? (mean, median, mode), Dispersion Measurements (range, quantiles, variance, standard deviation, outliers) and Shape Parameters / indicators (skewness, kurtosis) ?

Chapters:
00:00:00 - Sound check and introduction
00:05:49 - Overview of the lecture
00:10:58 - Answers to Assignments Lecture 3
01:13:00 - Break 1: Fox gifs
01:19:25 - Answers to Assignments Lecture 3 (Continued)
02:06:07 - Break 2: Wombat gifs
02:12:40 - Start of lecture 4
02:13:18 - Data APIs for Social Sciences
02:35:59 - Univariate versus Bivariate statistical analysis
02:38:04 - Central tendencies: Different types of means
02:45:00 - Central tendencies: Median
02:46:07 - Central tendencies: Mode
02:46:50 - Dispersion measures: Range
02:47:52 - Dispersion measures: Quantiles
02:49:33 - Dispersion measures: Variance & Standard Deviation
02:52:24 - Outliers and Data Winsorizing
02:57:27 - Shape measures: Skewness
02:58:35 - Shape measures: Kurtosis (Meso, Lepto, Platy)
03:00:00 - Normality in statistical tests
03:01:30 - Shapiro-Wilk normality testing in R
03:02:33 - Plots for univariate statistics
03:11:00 - Graphical parameters in R
03:12:03 - How to create a plot in R
03:14:30 - Multiple plots in a single R window
03:16:17 - Apply and subset functions in R
03:18:52 - Next week, Questions & outro

#rlanguage #programmingforstudents #lectureseries #statistics #assignments #coding #livestream #socialscience #lectures #playlist #education #educationalvideos #msc #phd #english #statisticsfordatascience #academia #academicyoutube #rpackages #answers #distributions #skewness #kurtosis #statistics #univariate #winsorizing #dispersion #normality #socialscience #api #outliers #plotting #descriptivestatistics

[paulosergioschlogl]

Thats awesome. I need to implement this kind of code in python " max(1, nrow(data) + 1): ncol(big_matrix) " ...thanks Danny🙃

[samuelokafor]

Hi Danny,
I could not extract this data despite using WinRaR to try and do so. The file appears to be corrupted. What can be done to remedy this.

Best,
Samuel

[bostonwren]

Guten tag! After 3 weeks' learning of R and Python, I find that clean data is so far the most difficult thing. 🤣

[ler]

Hey professor Danny, could you please explain this code for question 4b?
"for (x in
Are you iterating through both the rows and columns of the matrix simultaneously? I didn't know you could do that 😅 thanks in advance!

[paulosergioschlogl]

Danny it is trick to read a fasta file. In that case It is not better use a package like seqinr? That is specialized to deal with this kind of data?

[paulosergioschlogl]

In my case data2 has a lot of space between the header(seq names) and the sequences. And when I assign the names to sequences it looks like data2...

[paulosergioschlogl]

But Danny when you explained basic plot and watching some ggplot videos it works similar. Because ggplot works in layers too...but, I maybe wrong.

[paulosergioschlogl]

Hey Danny do you use windows OS for bioinfo? Sorry to ask...8)

[safaaandarawi]

Thank you Danny, Your lesson helped me a lot in my learning . I have a problem with changing the directory.r saying cannot change the working directory. I am working on a virtual machine that you made in the RNA seq pipeline video.can you help me with that