Prochaines sessions
Programme
Workflow:
- Using R Studio
- Using RStudio projetcs
- Using a simple files organisation method
- Using rmarkdown files
- Using a Version Control
- Setting Global Options
Import data sets:
- How to import csv file?
- How to import text file?
- How to import zip file?
Note:
- To go further
Cleaning and validation:
- Checking importation
- Checking data structure
- The useful format for tabular data: tidy
- Manage problems of data structure
- Rename variables
- Rename levels
- Management of missing values (NA)
- Identify absurd values
- Detecting outliers
Working with data :
- The package dplyr
- Select rows with filter()
- Select columns with the select() function
- Create new variable using mutate() function
- Summarise data with summarise_*’ functions
- Use the group_by() function
- The arrange() function
Combine rows and join columns:
- Combining rows
- Joining columns
Descriptive analysis:
- Interesting pacakages
- Data
- Missing, zeros and infinite values
- Descriptive analysis for factors
- Descriptive analysis for numeric variables
Dates and times with R:
- Introduction
- Standardised format for dates times
- Modification of the dates/times format and class
- Keep only date
- Rounding
- Manipulate date data
- Other things
Data visualisation:
- About ggplot2
- Principle of ggplot2
- Making scatterplots with ggplot2
- Make barplots with ggplot2
- Facetting
- Back to the concept of mapping with the aes() function
- Plotting time series
- More things
Regression analysis:
- Introduction
- The data: the cysfibr dataset
- Data management
- Assessment of linearity assumption
- Exploring multicollinearity
- Fitting the complete model
- Checking assumptions
- Results interpretation
- Adjustement of pvalues
- Selection of variables
- Plotting your results
Regression analysis with time (chronological data / longitudinal data):
- Introduction
- Data
- Fit the linear regression model
- Assessment of the residuals independce assumption
- Adding and AR1 correlation structure
- Assessments of residuals normality and homogeneity assumptions
- Plot your model
Principal Component Analysis :
- Principle
- How to run a PCA with R?
- Plot your results
- Ressources